Why the EU AI Act Matters for Agentic AI

Artificial intelligence is evolving rapidly. We’re moving from prompt-based systems to more autonomous, goal-driven technologies known as agentic AI. These systems can take independent actions, collaborate with other agents, and interact with external systems—all with limited human input. This shift introduces serious questions about governance, oversight, and security.

The EU Artificial Intelligence Act (EU AI Act) is the first major regulatory framework to address AI safety and compliance at scale. Based on a risk-based classification model, it sets clear, enforceable obligations for how AI systems are built, deployed, and managed. In addition to the core legislation, the European Commission will release a voluntary AI Code of Practice by mid-2025 to support industry readiness.

As agentic AI becomes more common in real-world systems, organizations must prepare now. These systems often fall into regulatory gray areas due to their autonomy, evolving behavior, and ability to operate across environments. Companies using or developing agentic AI need to evaluate how these technologies align with EU AI Act requirements—and whether additional internal safeguards are needed to remain compliant and secure.

This blog outlines how the EU AI Act may apply to agentic AI systems, where regulatory gaps exist, and how organizations can strengthen oversight and mitigate risk using purpose-built solutions like HiddenLayer.

What Is Agentic AI?

Agentic AI refers to systems that can autonomously perform tasks, make decisions, design workflows, and interact with tools or other agents to accomplish goals. While human users typically set objectives, the system independently determines how to achieve them. These systems differ from traditional generative AI, which typically responds to inputs without initiative, in that they actively execute complex plans.

Key Capabilities of Agentic AI:

• Autonomy: Operates with minimal supervision by making decisions and executing tasks across environments.
• Reasoning: Uses internal logic and structured planning to meet objectives, rather than relying solely on prompt-response behavior.
• Resource Orchestration: Calls external tools or APIs to complete steps in a task or retrieve data.
• Multi-Agent Collaboration: Delegates tasks or coordinates with other agents to solve problems.
• Contextual Memory: Retains past interactions and adapts based on new data or feedback.

IBM reports that 62% of supply chain leaders already see agentic AI as a critical accelerator for operational speed. However, this speed comes with complexity, and that requires stronger oversight, transparency, and risk management.

For a deeper technical breakdown of these systems, see our blog: Securing Agentic AI: A Beginner’s Guide.

Where the EU AI Act Falls Short on Agentic Systems

Agentic systems offer clear business value, but their unique behaviors pose challenges for existing regulatory frameworks. Below are six areas where the EU AI Act may need reinterpretation or expansion to adequately cover agentic AI.

1. Lack of Definition

The EU AI Act doesn’t explicitly define “agentic systems.” While its language covers autonomous and adaptive AI, the absence of a direct reference creates uncertainty. Recital 12 acknowledges that AI can operate independently, but further clarification is needed to determine how agentic systems fit within this definition, and what obligations apply.

2. Risk Classification Limitations

The Act assigns AI systems to four risk levels: unacceptable, high, limited, and minimal. But agentic AI may introduce context-dependent or emergent risks not captured by current models. Risk assessment should go beyond intended use and include a system’s level of autonomy, the complexity of its decision-making, and the industry in which it operates.

3. Human Oversight Requirements

The Act mandates meaningful human oversight for high-risk systems. Agentic AI complicates this: these systems are designed to reduce human involvement. Rather than eliminating oversight, this highlights the need to redefine oversight for autonomy. Organizations should develop adaptive controls, such as approval thresholds or guardrails, based on the risk level and system behavior.

4. Technical Documentation Gaps

While Article 11 of the EU AI Act requires detailed technical documentation for high-risk AI systems, agentic AI demands a more comprehensive level of transparency. Traditional documentation practices such as model cards or AI Bills of Materials (AIBOMs) must be extended to include:

• Decision pathways
• Tool usage logic
• Agent-to-agent communication
• External tool access protocols

This depth is essential for auditing and compliance, especially when systems behave dynamically or interact with third-party APIs.

5. Risk Management System Complexity

Article 9 mandates that high-risk AI systems include a documented risk management process. For agentic AI, this must go beyond one-time validation to include ongoing testing, real-time monitoring, and clearly defined response strategies. Because these systems engage in multi-step decision-making and operate autonomously, they require continuous safeguards, escalation protocols, and oversight mechanisms to manage the emergent and evolving risks they pose throughout their lifecycle.

6. Record-Keeping for Autonomous Behavior

Agentic systems make independent decisions and generate logs across environments. Article 12 requires event recording throughout the AI lifecycle. Structured logs, including timestamps, reasoning chains, and tool usage, are critical for post-incident analysis, compliance, and accountability.

The Cost of Non-Compliance

The EU AI Act imposes steep penalties for non-compliance:

• Up to €35 million or 7% of global annual turnover for prohibited practices
• Up to €15 million or 3% for violations involving high-risk AI systems
• Up to €7.5 million or 1% for providing false information

These fines are only part of the equation. Reputational damage, loss of customer trust, and operational disruption often cost more than the fine itself. Proactive compliance builds trust and reduces long-term risk.

Unique Security Threats Facing Agentic AI

Agentic systems aren’t just regulatory challenges. They also introduce new attack surfaces. These include:

• Prompt Injection: Malicious input embedded in external data sources manipulates agent behavior.
• PII Leakage: Unintentional exposure of sensitive data while completing tasks.
• Model Tampering: Inputs crafted to influence or mislead the agent’s decisions.
• Data Poisoning: Compromised feedback loops degrade agent performance.
• Model Extraction: Repeated querying reveals model logic or proprietary processes.

These threats jeopardize operational integrity and compliance with the EU AI Act’s demands for transparency, security, and oversight.

How HiddenLayer Supports Agentic AI Security and Compliance

At HiddenLayer, we’ve developed solutions designed specifically to secure and govern agentic systems. Our AI Detection and Response (AIDR) platform addresses the unique risks and compliance challenges posed by autonomous agents.

Human Oversight

AIDR enables real-time visibility into agent behavior, intent, and tool use. It supports guardrails, approval thresholds, and deviation alerts, making human oversight possible even in autonomous systems.

Technical Documentation

AIDR automatically logs agent activities, tool usage, decision flows, and escalation triggers. These logs support Article 11 requirements and improve system transparency.

Risk Management

AIDR conducts continuous risk assessment and behavioral monitoring. It enables:

• Anomaly detection during task execution
• Sensitive data protection enforcement
• Prompt injection defense

These controls support Article 9’s requirement for risk management across the AI system lifecycle.

Record-Keeping

AIDR structures and stores audit-ready logs to support Article 12 compliance. This ensures teams can trace system actions and demonstrate accountability.

By implementing AIDR, organizations reduce the risk of non-compliance, improve incident response, and demonstrate leadership in secure AI deployment.

What Enterprises Should Do Next

Even if the EU AI Act doesn’t yet call out agentic systems by name, that time is coming. Enterprises should take proactive steps now:

• Assess Your Risk Profile: Understand where and how agentic AI fits into your organization’s operations and threat landscape.
• Develop a Scalable AI Strategy: Align deployment plans with your business goals and risk appetite.
• Build Cross-Functional Governance: Involve legal, compliance, security, and engineering teams in oversight.
• Invest in Internal Education: Ensure teams understand agentic AI, how it operates, and what risks it introduces.
• Operationalize Oversight: Adopt tools and practices that enable continuous monitoring, incident detection, and lifecycle management.

Being early to address these issues is not just about compliance. It’s about building a secure, resilient foundation for AI adoption.

Conclusion

As AI systems become more autonomous and integrated into core business processes, they present both opportunity and risk. The EU AI Act offers a structured framework for governance, but its effectiveness depends on how organizations prepare.

Agentic AI systems will test the boundaries of existing regulation. Enterprises that adopt proactive governance strategies and implement platforms like HiddenLayer’s AIDR can ensure compliance, reduce risk, and protect the trust of their stakeholders.

Now is the time to act. Compliance isn’t a checkbox, it’s a competitive advantage in the age of autonomous AI.

Have questions about how to secure your agentic systems? Talk to a HiddenLayer team member today: contact us.

Introduction

Artificial intelligence (AI) has rapidly evolved from a cutting-edge technology into a foundational layer of modern digital infrastructure. Its influence is reshaping industries, redefining public services, and creating new vectors of economic and national competitiveness. In this environment, we need to change the narrative of “how to strike a balance between regulation and innovation” to “how to maximize performance across all dimensions of AI development”.

The AI industry must approach policy not as a constraint to be managed, but as a performance frontier to be optimized. Rather than framing regulation and innovation as competing forces, we should treat AI governance as a multidimensional challenge, where leadership is defined by the industry’s ability to excel across every axis of responsible development. That includes proactive engagement with oversight, a strong security posture, rigorous evaluation methods, and systems that earn and retain public trust.

The U.S. Approach to AI Policy

Historically, the United States has favored a decentralized, innovation-forward model for AI development, leaning heavily on sector-specific norms and voluntary guidelines.

• The American AI Initiative (2019) emphasized R&D and workforce development but lacked regulatory teeth.
  
• The Biden Administration’s 2023 Executive Order on Safe, Secure, and Trustworthy AI marked a stronger federal stance, tasking agencies like NIST with expanding the AI Risk Management Framework (AI RMF).
  
• While the subsequent administration rescinded this order in 2025, it ignited industry-wide momentum around responsible AI practices.
  

States are also taking independent action. Colorado’s SB21-169 and California’s CCPA expansions reflect growing demand for transparency and accountability, but also introduce regulatory fragmentation. The result is a patchwork of expectations that slows down oversight and increases compliance complexity.

Federal agencies remain siloed:

• FTC is tackling deceptive AI claims.
  
• FDA is establishing pathways for machine-learning medical tools.
  
• NIST continues to lead with voluntary but influential frameworks.
  

This fragmented landscape presents the industry with both a challenge and an opportunity to lead in building innovative and governable systems.

AI Governance as a Performance Metric

In many policy circles, AI oversight is still framed as a “trade-off,” with innovation on one side and regulation on the other. But this is a false dichotomy. In practice, the capabilities that define safe, secure, and trustworthy AI systems are not in tension with innovation, they are essential components of it.

• Security posture is not simply a compliance requirement; it is foundational to model integrity and resilience. Whether defending against adversarial attacks or ensuring secure data pipelines, AI systems must meet the same rigor as traditional software infrastructure, if not higher.
• Fairness and transparency are not checkboxes but design challenges. AI tools used in hiring, lending, or criminal justice must function equitably across demographic groups. Failures in these areas have already led to real-world harms, such as flawed facial recognition leading to false arrests or automated résumé screening systems reinforcing gender and racial biases.
• Explainability is key to adoption and accountability. In healthcare, clinicians using AI-based diagnostics need clear reasoning from models to make safe decisions, just as patients need to trust the tools shaping their outcomes. When these capabilities are missing, the issue isn’t just regulatory, it’s performance. A system that is biased, brittle, or opaque is not only untrustworthy but also fundamentally incomplete. High-performance AI development means building for resilience, reliability, and inclusion in the same way we design for speed, scale, and accuracy.

The industry’s challenge is to embrace regulatory readiness as a marker of product maturity and competitive advantage, not a burden. Organizations that develop explainability tooling, integrate bias auditing, or adopt security standards early will not only navigate policy shifts more easily but also likely build better, more trusted systems.

A Smarter Path to AI Oversight

One of the most pragmatic paths forward is to adapt existing regulatory frameworks that already govern software, data, and risk rather than inventing an entirely new regime for AI.

Rather than starting from scratch, the U.S. can build on proven regulatory frameworks already used in cybersecurity, privacy, and software assurance.

• NIST Cybersecurity Framework (CSF) offers a structured model for threat identification and response that can extend to AI security.
  
• FISMA mandates strong security programs in federal agencies—principles that can guide government AI system protections.
  
• GLBA and HIPAA offer blueprints for handling sensitive data, applicable to AI systems dealing with personal, financial, or biometric information.
  

These frameworks give both regulators and developers a shared language. Tools like model cards, dataset documentation, and algorithmic impact assessments can sit on top of these foundations, aligning compliance with transparency.

Industry efforts, such as Google’s Secure AI Framework (SAIF), reflect a growing recognition that AI security must be treated as a core engineering discipline, not an afterthought.

Similarly, NIST’s AI RMF encourages organizations to embed risk mitigation into development workflows, an approach closely aligned with HiddenLayer’s vision for secure-by-design AI.

One emerging model to watch: regulatory sandboxes. Inspired by the U.K.’s Financial Conduct Authority, sandboxes allow AI systems to be tested in controlled environments alongside regulators. This enables innovation without sacrificing oversight.

Conclusion: AI Governance as a Catalyst, Not a Constraint

The future of AI policy in the United States should not be about compromise, it should be about optimization. The AI industry must rise to the challenge of maximizing performance across all core dimensions: innovation, security, privacy, safety, fairness, and transparency. These are not constraints, but capabilities and necessary conditions for sustainable, scalable, and trusted AI development.

By treating governance as a driver of excellence rather than a limitation, we can strengthen our security posture, sharpen our innovation edge, and build systems that serve all communities equitably. This is not a call to slow down. It is a call to do it right, at full speed.

The tools are already within reach. What remains is a collective commitment from industry, policymakers, and civil society to make AI governance a function of performance, not politics. The opportunity is not just to lead the world in AI capability but also in how AI is built, deployed, and trusted.

At HiddenLayer, we’re committed to helping organizations secure and scale their AI responsibly. If you’re ready to turn governance into a competitive advantage, contact our team or explore how our AI security solutions can support your next deployment.

RSA Conference 2025 may be over, but conversations are still echoing about what’s possible with AI and what’s at risk. This year’s theme, “Many Voices. One Community,” reflected the growing understanding that AI security isn’t a challenge one company or sector can solve alone. It takes shared responsibility, diverse perspectives, and purposeful collaboration.

After a week of keynotes, packed sessions, analyst briefings, the Security for AI Council breakfast, and countless hallway conversations, our team returned with a renewed sense of purpose and validation. Protecting AI requires more than tools. It requires context, connection, and a collective commitment to defending innovation at the speed it’s moving.

Below are five key takeaways that stood out to us, informed by our CISO Malcolm Harkins’ reflections and our shared experience at the conference

1. Agentic AI is the Next Big Challenge

Agentic AI was everywhere this year, from keynotes to vendor booths to panel debates. These systems, capable of taking autonomous actions on behalf of users, are being touted as the next leap in productivity and defense. But they also raise critical concerns: What if an agent misinterprets intent? How do we control systems that can act independently? Conversations throughout RSAC highlighted the urgent need for transparency, oversight, and clear guardrails before agentic systems go mainstream.

While some vendors positioned agents as the key to boosting organizational defense, others voiced concerns about their potential to become unpredictable or exploitable. We’re entering a new era of capability, and the security community is rightfully approaching it with a mix of optimism and caution.

2. Security for AI Begins with Context

During the Security for AI Council breakfast, CISOs from across industries emphasized that context is no longer optional, but foundational. It’s not just about tracking inputs and outputs, but understanding how a model behaves over time, how users interact with it, and how misuse might manifest in subtle ways. More data can be helpful, but it’s the right data, interpreted in context, that enables faster, smarter defense.

As AI systems grow more complex, so must our understanding of their behaviors in the wild. This was a clear theme in our conversations, and one that HiddenLayer is helping to address head-on.

3. AI’s Expanding Role: Defender, Adversary, and Target

This year, AI wasn’t a side topic but the centerpiece. As our CISO, Malcolm Harkins, noted, discussions across the conference explored AI’s evolving role in the cyber landscape:

• Defensive applications: AI is being used to enhance threat detection, automate responses, and manage vulnerabilities at scale.
• Offensive threats: Adversaries are now leveraging AI to craft more sophisticated phishing attacks, automate malware creation, and manipulate content at a scale that was previously impossible.
• AI itself as a target: Like many technology shifts before it, security has often lagged deployment. While the “risk gap”, the time between innovation and protection, may be narrowing thanks to proactive solutions like HiddenLayer, the fact remains: many AI systems are still insecure by default.

AI is no longer just a tool to protect infrastructure. It is the infrastructure, and it must be secured as such. While the gap between AI adoption and security readiness is narrowing, thanks in part to proactive solutions like HiddenLayer’s, there’s still work to do.

4. We Can’t Rely on Foundational Model Providers Alone

In analyst briefings and expert panels, one concern repeatedly came up: we cannot place the responsibility of safety entirely on foundational model providers. While some are taking meaningful steps toward responsible AI, others are moving faster than regulation or safety mechanisms can keep up.

The global regulatory environment is still fractured, and too many organizations are relying on vendors’ claims without applying additional scrutiny. As Malcolm shared, this is a familiar pattern from previous tech waves, but in the case of AI, the stakes are higher. Trust in these systems must be earned, and that means building in oversight and layered defense strategies that go beyond the model provider. Current research, such as Universal Bypass, demonstrates this.

5. Legacy Themes Remain, But AI Has Changed the Game

RSAC 2025 also brought a familiar rhythm, emphasis on identity, Zero Trust architectures, and public-private collaboration. These aren’t new topics, but they continue to evolve. The security community has spent over a decade refining identity-centric models and pushing for continuous verification to reduce insider risk and unauthorized access.

For over twenty years, the push for deeper cooperation between government and industry has been constant. This year, that spirit of collaboration was as strong as ever, with renewed calls for information sharing and joint defense strategies.

What’s different now is the urgency. AI has accelerated both the scale and speed of potential threats, and the community knows it. That urgency has moved these longstanding conversations from strategic goals to operational imperatives.

Looking Ahead

The pace of innovation on the expo floor was undeniable. But what stood out even more were the authentic conversations between researchers, defenders, policymakers, and practitioners. These moments remind us what cybersecurity is really about: protecting people.

That’s why we’re here, and that’s why HiddenLayer exists. AI is changing everything, from how we work to how we secure. But with the right insights, the right partnerships, and a shared commitment to responsibility, we can stay ahead of the risk and make space for all the good AI can bring.

RSAC 2025 reminded us that AI security is about more than innovation. It’s about accountability, clarity, and trust. And while the challenges ahead are complex, the community around them has never been stronger.

Together, we’re not just reacting to the future.
We’re helping to shape it.

HiddenLayer researchers have developed the first single, universal prompt injection technique, post-instruction hierarchy, that successfully bypasses safety guardrails across nearly all major frontier AI models. This includes models from OpenAI (GPT-4o, GPT-4o-mini, and even the newly announced GPT-4.1), Google (Gemini 1.5, 2.0, and 2.5), Microsoft (Copilot), Anthropic (Claude 3.7 and 3.5), Meta (Llama 3 and 4 families), DeepSeek (V3, R1), Qwen (2.5 72B), and Mixtral (8x22B).

The technique, dubbed Prompt Puppetry, leverages a novel combination of roleplay and internally developed policy techniques to circumvent model alignment, producing outputs that violate safety policies, including detailed instructions on CBRN threats, mass violence, and system prompt leakage. The technique is not model-specific and appears transferable across architectures and alignment approaches.

The research provides technical details on the bypass methodology, real-world implications for AI safety and risk management, and the importance of proactive security testing, especially for organizations deploying or integrating LLMs in sensitive environments.

Threat actors now have a point-and-shoot approach that works against any underlying model, even if they do not know what it is. Anyone with a keyboard can now ask how to enrich uranium, create anthrax, or otherwise have complete control over any model. This threat shows that LLMs cannot truly self-monitor for dangerous content and reinforces the need for additional security tools.

Is it Patchable?

It would be extremely difficult for AI developers to properly mitigate this issue. That’s because the vulnerability is rooted deep in the model’s training data, and isn’t as easy to fix as a simple code flaw. Developers typically have two unappealing options:

1. Re-tune the model with additional reinforcement learning (RLHF) in an attempt to suppress this specific behavior. However, this often results in a “whack-a-mole” effect. Suppressing one trick just opens the door for another and can unintentionally degrade model performance on legitimate tasks.
2. Try to filter out this kind of data from training sets, which has proven infeasible for other types of undesirable content. These filtering efforts are rarely comprehensive, and similar behaviors often persist.

That’s why external monitoring and response systems like HiddenLayer’s AISec Platform are critical. Our solution doesn’t rely on retraining or patching the model itself. Instead, it continuously monitors for signs of malicious input manipulation or suspicious model behavior, enabling rapid detection and response even as attacker techniques evolve.

Impacting All Industries

In domains like healthcare, this could result in chatbot assistants providing medical advice that they shouldn’t, exposing private patient data, or invoking medical agent functionality that shouldn’t be exposed.

In finance, AI analysis of investment documentation or public data sources like social media could result in incorrect financial advice or transactions that shouldn’t be approved as well as utilize chatbots to expose sensitive customer financial data & PII.

In manufacturing, the greatest fear isn’t always a cyberattack but downtime. Every minute of halted production directly impacts output, reduces revenue, and can drive up product costs. AI is increasingly being adopted to optimize manufacturing output and reduce those costs. However, if those AI models are compromised or produce inaccurate outputs, the result could be significant: lost yield, increased operational costs, or even the exposure of proprietary designs or process IP.

Increasingly, airlines are utilizing AI to improve maintenance and provide crucial guidance to mechanics to ensure maximized safety. If compromised, and misinformation is provided, faulty maintenance could occur, jeopardizing
public safety.

In all industries, this could result in embarrassing customer chatbot discussions about competitors, transcripts of customer service chatbots acting with harm toward protected classes, or even misappropriation of public-facing AI systems to further CBRN (Chemical, Biological, Radiological, and Nuclear), mass violence, and self-harm.

AI Security has Arrived

Inside HiddenLayer’s AISec Platform and AIDR: The Defense System AI Has Been Waiting For

While model developers scramble to contain vulnerabilities at the root of LLMs, the threat landscape continues to evolve at breakneck speed. The discovery of Prompt Puppetry proves a sobering truth: alignment alone isn’t enough. Guardrails can be jumped. Policies can be ignored. HiddenLayer’s AISec Platform, powered by AIDR—AI Detection & Response—was built for this moment, offering intelligent, continuous oversight that detects prompt injections, jailbreaks, model evasion techniques, and anomalous behavior before it causes harm. In highly regulated sectors like finance and healthcare, a single successful injection could lead to catastrophic consequences, from leaked sensitive data to compromised model outputs. That’s why industry leaders are adopting HiddenLayer as a core component of their security stack, ensuring their AI systems stay secure, monitored, and resilient.

Request a demo with HiddenLayer to learn more

Artificial Intelligence is entering a new chapter defined not just by generating content but by taking independent, goal-driven action. This evolution is called agentic AI. These systems don’t simply respond to prompts; they reason, make decisions, contact tools, and carry out tasks across systems, all with limited human oversight. In short, they are the architects of their own workflows.

But with autonomy comes complexity and risk. Agentic AI creates an expanded attack surface that traditional cybersecurity tools weren’t designed to defend.

That’s where AI Detection & Response (AIDR) comes in.

Built by HiddenLayer, AIDR is a purpose-built platform for securing AI in all its forms,  including agentic systems. It offers real-time defense, complete visibility, and deep control over the agentic execution stack, enabling enterprises to adopt autonomous AI safely.

What Makes Agentic AI Different?

To understand why traditional security falls short, you have to understand what makes agentic AI fundamentally different.

While conventional generative AI systems produce single outputs from prompts, agentic AI goes several steps further. These systems reason through multi-step tasks, plan over time, access APIs and tools, and even collaborate with other agents. Often, they make decisions that impact real systems and sensitive data, all without immediate oversight.

The critical difference? In agentic systems, the large language model (LLM) generates content but also drives logic and execution.

This evolution introduces:

• Autonomous Execution Paths: Agents determine their own next steps and iterate as they go.
• Deep API & Tool Integration: Agents directly interact with systems through code, not just natural language.
• Stateful Memory: Memory enhances task continuity but also increases the attack surface.
• Multi-Agent Collaboration: Coordinated behavior raises the risk of lateral compromise and cascading failures.

The result is a fundamentally new class of software: intelligent, autonomous, and deeply embedded in business operations.

Security Challenges in Agentic AI

Agentic AI’s strengths are also its vulnerabilities. Designed for independence, these systems can be manipulated without proper controls.

The risks include:

• Indirect Prompt Injection — A technique where attackers embed hidden or harmful instructions external content to manipulate an agent’s behavior or bypass its guardrails.
• PII Leakage — The unintended exposure of sensitive or personally identifiable information during an agent’s interactions or task execution.
• Model Tampering — The use of carefully crafted inputs to exploit vulnerabilities in the model, leading to skewed outputs or erratic behavior.
• Data Poisoning / Model Injection — The deliberate introduction of misleading or harmful data into training or feedback loops, altering how the agent learns or responds.
• Model Extraction / Theft — An attack that uses repeated queries to reverse-engineer an AI model, allowing adversaries to replicate its logic or steal intellectual property.

How AIDR Protects Agentic AI

HiddenLayer’s AI Detection and Response (AIDR) was designed to secure AI systems in production. Unlike traditional tools that focus only on input/output, AIDR monitors intent, behavior, and system-level interactions. It’s built to understand what agents are doing, how they’re doing it, and whether they’re staying aligned with their objectives.

Core protection capabilities include:

• Agent Activity Monitoring: Monitors and logs agent behavior to detect anomalies during execution.
• Sensitive Data Protection: Detects and blocks the unintended leakage of PII or confidential information in outputs.
• Knowledge Base Protection: Detects prompt injections in data accessed by agents to maintain source integrity.

Together, these layers give security teams peace of mind, ensuring autonomous agents remain aligned, even when operating independently.

Built for Modern Enterprise Platforms

AIDR protects real-world deployments across today’s most advanced agentic platforms:

• OpenAI Agent SDK.
• Custom agents using LangChain, MCP, AutoGen, LangGraph, n8n and more.
• Low-Friction Setup: Works across cloud, hybrid, and on-prem environments.

Each integration is designed for platform-specific workflows, permission models, and agent behaviors, ensuring precise, contextual protection. 

Adapting to Evolving Threats

HiddenLayer’s AIDR platform evolves alongside new and emerging threats with input from:

• Threat Intelligence from HiddenLayer’s Synaptic Adversarial Intelligence (SAI) Team
• Behavioral Detection Models to surface intent-based risks
• Customer Feedback Loops for rapid tuning and responsiveness

This means defenses will keep up as agents grow more powerful and more complex.

Why Securing Agentic AI Matters

Agentic AI can transform your business, but only if it’s secure. With AI Detection and Response, organizations can:

• Accelerate adoption by removing security barriers
• Prevent data loss, misuse, or rogue automation
• Stay compliant with emerging AI regulations
• Protect brand trust by avoiding catastrophic failures
• Reduce manual oversight with automated safeguards

The Road Ahead

Agentic AI is already reshaping enterprise operations. From development pipelines to customer experience, agents are becoming key players in the modern digital stack.

The opportunity is massive, and so is the responsibility. AIDR ensures your agentic AI systems operate with visibility, control, and trust. It’s how we secure the age of autonomy.

At HiddenLayer, we’re securing the age of agency. Let’s build responsibly.

Want to see how AIDR secures Agentic AI? Schedule a demo here.

The past year brought significant advancements in AI across multiple domains, including multimodal models, retrieval-augmented generation (RAG), humanoid robotics, and agentic AI.

Multimodal models

Multimodal models became popular with the launch of OpenAI’s GPT-4o. What makes a model “multimodal” is its ability to create multimedia content (images, audio, and video) in response to text- or audio-based prompts, or vice versa, respond with text or audio to multimedia content uploaded to a prompt. For example, a multimodal model can process and translate a photo of a foreign language menu. This capability makes it incredibly versatile and user-friendly. Equally, multimodality has seen advancement toward facilitating real-time, natural conversations.

While GPT-4o might be one of the most used multimodal models, it's certainly not singular. Other well-known multimodal models include KOSMOS and LLaVA from Microsoft, Gemini 2.0 from Google, Chameleon from Meta, and Claude 3 from Anthopic.

Retrieval-Augmented Generation

Another hot topic in AI is a technique called Retrieval-Augmented Generation (RAG). Although first proposed in 2020, it has gained significant recognition in the past year and is being rapidly implemented across industries. RAG combines large language models (LLMs) with external knowledge retrieval to produce accurate and contextually relevant responses. By having access to a trusted database containing the latest and most relevant information not included in the static training data, an LLM can produce more up-to-date responses less prone to hallucinations. Moreover, using RAG facilitates the creation of highly tailored domain-specific queries and real-time adaptability.

In September 2024, we saw the release of Oracle Cloud Infrastructure GenAI Agents - a platform that combines LLMs and RAG. In January 2025, a service that helps to streamline the information retrieval process and feed it to an LLM, called Vertex AI RAG Engine, was unveiled by Google.

Humanoid robots

The concept of humanoid machines can be traced as far back as ancient mythologies of Greece, Egypt, and China. However, the technology to build a fully functional humanoid robot has not matured sufficiently - until now. Rapid advancements in natural language have expedited machines’ ability to perform a wide range of tasks while offering near-human interactions.

Tesla's Optimus and Agility Robotics' Digit robot are at the forefront of these advancements. Optimus unveiled its second generation in December 2023, featuring significant improvements over its predecessor, including faster movement, reduced weight, and sensor-embedded fingers. Digit’s has a longer history, releasing and deploying it’s fifth version in June 2024 for use at large manufacturing factories.

Advancements in LLM technology are new driving factors for the field of robotics. In December 2023, researchers unveiled a humanoid robot called Alter3, which leverages GPT-4. Besides being used for communication, the LLM enables the robot to generate spontaneous movements based on linguistic prompts. Thanks to this integration, Alter3 can perform actions like adopting specific poses or sequences without explicit programming, demonstrating the capability to recognize new concepts without labeled examples.

Agentic AI

Agentic AI is the natural next step in AI development that will vastly enhance the way in which we use and interact with AI. Traditional AI bots heavily rely on pre-programmed rules and, therefore, have limited scope for independent decision-making. The goal of agentic AI is to construct assistants that would be unprecedentedly autonomous, make decisions without human feedback, and perform tasks without requiring intervention. Unlike GenAI, whose main functionality is generating content in response to user prompts, agentic assistants are focused on optimizing specific goals and objectives - and do so independently. This can be achieved by assembling a complex network of specialized models (“agents”), each with a particular role and task, as well as access to memory and external tools. This technology has incredible promise across many sectors, from manufacturing to health to sales support and customer service, and is being trialed and tested for live implementation.

Google has been investing heavily over the past year in the development of agentic models, and the new version of their flagship generative AI, Gemini 2.0, is specially designed to help build AI agents. Moreover, OpenAI released a research preview of their first autonomous agentic AI tool called Operator. Operator is an agent able to perform a range of different tasks on the website independently, and it can be used to automate various browser related activities, such as placing online orders and filling out online forms.

We’re already seeing Agentic AI turbocharged with the integration of multimodal models into agentic robotics and the concept of agentic RAG. Combining the advancements of these technologies, the future of powerful and complex autonomous solutions will soon transcend imagination into reality. 

The Rise of Open-weight Models

Open-weight models are models whose weights (i.e., the output of the model training process) are made available to the broader public. This allows users to implement the model locally, adapt it, and fine-tune it without the constraints of a proprietary model. Traditionally, open-weight models were scoring lower against leading proprietary models in AI performance benchmarking. This is because training a large GenAI solution requires tremendous computing power and is, therefore, incredibly expensive. The biggest players on the market, who are able to afford to train a high-quality GenAI, usually keep their models ringfenced and only allow access to the inference API. The recent release of an open-weight DeepSeek-R1 model might be on course to disrupt this trend.

In January 2025, a Chinese AI lab called DeepSeek released several open-weight foundation models that performed comparably in reasoning performance to top close-weight models from OpenAI. DeepSeek claims the cost of training the models was only $6M, which is significantly lower than average. Moreover, reviewing the pricing of DeepSeek-R1 API against the popular OpenAI-o1 API shows the DeepSeek model is approximately 27x cheaper than o1 to operate, making it a very tempting option for a cost-conscious developer.

DeepSeek models might look like a breakthrough in AI training and deployment costs; however, upon a closer look, these models are ridden with problems, from insufficient safety guardrails, to insecure loading, to embedded bias and data privacy concerns.

As frontier-level open-weight models are likely to proliferate, deploying such models should be done with utmost caution. Models released by untrusted entities might contain security flaws, biases, and hidden backdoors and should be carefully evaluated prior to local deployment. People choosing to use hosted solutions should also be acutely aware of privacy issues concerning the prompts they send to these models.

Introduction

The rise of generative AI has unlocked new possibilities across industries, and among the most promising developments is the emergence of agentic AI. Unlike traditional AI systems that respond to isolated prompts, agentic AI systems can plan, reason, and take autonomous action to achieve complex goals.

In a recent webinar poll conducted by Gartner in January 2025, 64% of respondents indicated that they plan to pursue agentic AI initiatives within the next year. But what exactly is agentic AI? How does it work? And what should organizations consider when deploying these systems, especially from a security standpoint?

As the term agentic AI becomes more widely used, it’s important to distinguish between two emerging categories of agents. On one side, there are “computer use” agents, such as OpenAI’s Operator or Claude’s Computer Use, designed to navigate desktop environments like a human, using interfaces like keyboards and screen inputs. These systems often mimic human behavior to complete general-purpose tasks and may introduce new risks from indirect prompt injections or as a form of shadow AI. On the other side are business logic or application-specific agents, such as Copilot agents or n8n flows, which are built to interact with predefined APIs or systems under enterprise governance. This blog primarily focuses on the second category: enterprise-integrated agentic systems, where security and oversight are essential to safe deployment. 

This beginner’s guide breaks down the foundational concepts behind agentic AI and provides practical advice for safe and secure adoption.

What Is Agentic AI?

Agentic AI refers to artificial intelligence systems that demonstrate agency — the ability to autonomously pursue goals by making decisions, executing actions, and adapting based on feedback. These systems extend the capabilities of large language models (LLMs) by adding memory, tool access, and task management, allowing them to operate more like intelligent agents than simple chatbots.

Essentially, agentic AI is about transforming LLMs into AI agents that can proactively solve problems, take initiative, and interact with their environment.

Key Capabilities of Agentic AI Systems:

• Autonomy: Operate independently without constant human input.
• Goal Orientation: Pursue high-level objectives through multiple steps.
• Tool Use: Invoke APIs, search engines, file systems, and even other models.
• Memory and Reflection: Retain and use information from past interactions to improve performance.

These core features enable agentic systems to execute complex, multi-step tasks across time, which is a major advancement in the evolution of AI.

How Does Agentic AI Work?

Most agentic AI systems are built on top of LLMs like GPT, Claude, or Gemini, using orchestration frameworks such as LangChain, AutoGen, or OpenAI’s Agents SDK. These frameworks enable developers to:

• Define tasks and goals
• Integrate external tools (e.g., databases, search, code interpreters)
• Store and manage memory
• Create feedback loops for iterative reasoning (plan → act → evaluate → repeat)

For example, consider an AI agent tasked with planning a vacation. Instead of simply answering “Where should I go in April?”, an agentic system might:

• Research destinations with favorable weather
• Check flight and hotel availability
• Compare options based on budget and preferences
• Build a full itinerary
• Offer to book the trip for you

This step-by-step reasoning and execution illustrates the agent’s ability to handle complex objectives with minimal oversight while utilizing various tools.

Real-World Use Cases of Agentic AI

Agentic AI is being adopted across sectors to streamline operations, enhance decision-making, and reduce manual overhead:

• Finance: AI agents generate real-time reports, detect fraud, and support compliance reviews.
• Cybersecurity: Agentic systems help triage threats, monitor activity, and flag anomalies.
• Customer Service: Virtual agents resolve multi-step tickets autonomously, improving response times.
• Healthcare: AI agents assist with literature reviews and decision support in diagnostics.
• DevOps: Code review bots and system monitoring agents help reduce downtime and catch bugs earlier.

The ability to chain tasks and interact with tools makes agentic AI highly adaptable across industries.

The Security Risks of Agentic AI

With greater autonomy comes a larger attack surface. According to a recent Gartner study, over 50% of successful cybersecurity attacks against AI agents will exploit access control issues in the coming year, using direct or indirect prompt injection as an attack vector. This being said, agentic AI systems introduce unique risks that organizations must address early:

• Prompt Injection: Malicious inputs can hijack the agent’s instructions or logic.
• Tool Misuse: Unrestricted access to external tools may result in unintended or harmful actions.
• Memory Poisoning: False or manipulated data stored in memory can influence future decisions.
• Goal Misalignment: Poorly defined goals can lead agents to optimize for unsafe or undesirable outcomes.

As these intelligent agents grow in complexity and capability, their security must evolve just as quickly.

Best Practices for Building Secure Agentic AI

Getting started with agentic AI doesn't have to be risky. If you implement foundational safeguards. Here are five essential best practices:

1. Start Simple: Limit the agent’s scope by restricting tasks, tools, and memory to reduce complexity.
2. Implement Guardrails: Define strict constraints on the agent’s tool access and behavior. For example, HiddenLayers AIDR can provide this capability today by identifying and responding to tool usage.
3. Log Everything: Record all actions and decisions for observability, auditing, and debugging.
4. Validate Inputs and Outputs: Regularly verify that the agent is functioning as intended.
5. Red Team Your Agents: Simulate adversarial attacks to uncover vulnerabilities and improve resilience.

By embedding security at the foundation, you’ll be better prepared to scale agentic AI safely and responsibly.

Final Thoughts

Agentic AI marks a major step forward in artificial intelligence's capabilities, bringing us closer to systems that can reason, act, and adapt like human collaborators. But these advancements come with real-world risks that demand attention.

Whether you're building your first AI agent or integrating agentic AI into your enterprise architecture, it’s critical to balance innovation with holistic security practices.

At HiddenLayer, the future of agentic AI can be both powerful and protected. If you're looking to explore how you can secure your agentic AI adoption, contact our team to book a demo.

Summary

Organizations deploying AI must ensure resilience against adversarial attacks before models go live. This blog covers best practices for AI red teaming, drawing on industry frameworks and insights from real-world engagements by HiddenLayer’s Professional Services team.

Framework & Considerations for Gen AI Red Teaming

OWASP is a leader in standardizing AI red teaming. Resources like the OWASP Top 10 for Large Language Models (LLMs) and the recently released GenAI Red Teaming Guide provide critical insights into how adversaries may target AI systems and offer helpful guidance for security leaders.

HiddenLayer has been a proud contributor to this work, partnering with OWASP’s Top 10 for LLM Applications and supporting community-driven security standards for GenAI.

The OWASP Top 10 for Large Language Model Applications has undergone multiple revisions, with the most recent version released earlier this year. This document outlines common threats to LLM applications, such as Prompt Injection and Sensitive Information Disclosure, which help shape the objectives of a red team engagement.

Complementing this, OWASP's GenAI Red Teaming Guide helps practitioners define the specific goals and scope of their testing efforts. A key element of the guide is the Blueprint for GenAI Red Teaming—a structured, phased approach to red teaming that includes planning, execution, and post-engagement processes (see Figure 4 below, reproduced from OWASP’s GenAI Red Teaming Guide). The Blueprint helps teams translate high-level objectives into actionable tasks, ensuring consistency and thoroughness across engagements.

Together, the OWASP Top 10 and the GenAI Red Teaming Guide provide a foundational framework for red teaming GenAI systems. The Top 10 informs what to test, while the Blueprint defines how to test it. Additional considerations, such as modality-specific risks or manual vs. automated testing, build on this core framework to provide a more holistic view of the red teaming strategy.

Defining the Objectives

With foundational frameworks like the OWASP Top 10 and the GenAI Red Teaming Guide in place, the next step is operationalizing them into a red team engagement. That begins with clearly defining your objectives. These objectives will shape the scope of testing, determine the tools and techniques used, and ultimately influence the impact of the red team’s findings. A vague or overly broad scope can dilute the effectiveness of the engagement. Clarity at this stage is essential.

1. Content Generation Testing: Can the model produce harmful outputs? If it inherently cannot generate specific content (e.g., weapon instructions), security controls preventing such outputs become secondary.
2. Implementation Controls: Examining system prompts, third-party guardrails, and defenses against malicious inputs.
3. Agentic AI Risks: Assessing external integrations and unintended autonomy, particularly for AI agents with decision-making capabilities.
4. Runtime Behaviors: Evaluating how AI-driven processes impact downstream business operations.

Automated Versus Manual Red Teaming

As we’ve discussed in depth previously, many open-source and commercial tools are available to organizations wishing to automate the testing of their generative AI deployments against adversarial attacks. Leveraging automation is great for a few reasons:

• A repeatable baseline for testing model updates.
• The ability to identify low-hanging fruit quickly.
• Efficiency in testing adversarial prompts at scale.

Certain automated red teaming tools, such as PyRIT, work by allowing red teams to specify an objective in the form of a prompt to an attacking LLM. This attacking LLM then dynamically generates prompts to send to the target LLM, refining its prompts based on the output of the target LLM until it hopefully achieves the red team’s objective. While such tools can be useful, it can take more time to refine one’s initial prompt to the attacking LLM than it would take just to attack the target LLM directly. For red teamers on an engagement with a limited time scope, this tradeoff needs to be considered beforehand to avoid wasting valuable time. 

Automation has limits. The nature of AI threats—where adversaries continually adapt—demands human ingenuity. Manual red teaming allows for dynamic, real-time adjustments that automation can’t replicate. The cat-and-mouse game between AI defenders and attackers makes human-driven testing indispensable.

Defining The Objectives

Arguably, the most important part of a red team engagement is defining the overall objectives of the test. A successful red team engagement starts with clear objectives. Organizations must define:

• Model Type & Modality: Attacks on text-based models differ from those on image or audio-based systems, which introduce attack possibilities like adversarial perturbations and hiding prompts within the image or audio channel.
• Testing Goals: Establishing clear objectives (e.g., prompt injection, data leakage) ensures both parties align on success criteria.

The OWASP GenAI Red Teaming Guide is a great starting point for new red teamers to define what these objectives will be. Without an industry-standard taxonomy of attacks, organizations will need to define their own potential objectives based on their own skillsets, expertise, and experience attacking genAI systems. These objectives can then be discussed and agreed upon before any engagement takes place. 

Following a Playbook

The process of establishing manual red teaming can be tedious, time-consuming, and can risk getting off track. This is where having a pre-defined playbook comes in handy. A playbook helps: 

• Map objectives to specific techniques (e.g., testing for "Generation of Toxic Content" via Prompt Injection or KROP attacks).
• Ensure consistency across engagements.
• Onboard less experienced red teamers faster by providing sample attack scenarios.

For example, if “Generation of Toxic Content” is an objective of a red team engagement, the playbook would list subsequent techniques that could be used to achieve this objective. A red teamer can refer to the playbook and see that something like Prompt Injection or KROP would be a valuable technique to test. For more mature red team organizations, sample prompts can be associated with techniques that will enable less experienced red teamers to ramp up quickly and provide value on engagements. 

Documenting and Sharing Results

The final task for a red team engagement is to ensure that all results are properly documented so that they can be shared with the client. An important consideration when sharing results is providing enough information and context so that the client can reproduce all results after the engagement. This includes providing all sample prompts, responses, and any tooling used to create adversarial input into the genAI system during the engagement. Since the goal of a red team engagement is to improve an organization’s security posture, being able to test the attacks after making security changes allows the clients to validate their efforts. 

Knowing that an AI system can be bypassed is an interesting data point. Understanding how to fix these issues is why red teaming is done. Every prompt and test done against an AI system must be done with the purpose of having a recommendation tied to how to prevent that attack in the future. Proving something can be broken without any method to fix it wastes the time of both the red teamers and the organization. 

All of these findings and recommendations should then be packaged up and presented to the appropriate stakeholders on both sides. Allowing the organization to review the results and ask questions of the red team can provide tremendous value. Seeing how an attack can unfold or discussing why an attack works enables organizations to fully grasp how to secure their systems and get the full value of a red team engagement. The ultimate goal isn’t just to uncover vulnerabilities but rather to strengthen AI security.

Conclusion

Effective AI red teaming combines industry best practices with real-world expertise. By defining objectives, leveraging automation alongside human ingenuity, and following structured methodologies, organizations can proactively strengthen AI security. If you want to learn more about AI red teaming, the HiddenLayer Professional Services team is here to help. Contact us to learn more.

Predictions for 2025

It’s time to dust off the crystal ball once again! Over the past year, AI has truly been at the forefront of cyber security, with increased scrutiny from attackers, defenders, developers, and academia. As various forms of generative AI drive mass AI adoption, we find that the threats are not lagging far behind, with LLMs, RAGs, Agentic AI, integrations, and plugins being a hot topic for researchers and miscreants alike.

Looking ahead, we expect the AI security landscape will face even more sophisticated challenges in 2025:

1. Agentic AI as a Target:
   Integrating agentic AI will blur the lines between adversarial AI and traditional cyberattacks, leading to a new wave of targeted threats. Expect phishing and data leakage via agentic systems to be a hot topic.
2. Erosion of Trust in Digital Content:
   As deepfake technologies become more accessible, audio, visual, and text-based digital content trust will face near-total erosion. Expect to see advances in AI watermarking to help combat such attacks.
3. Adversarial AI: Organizations will integrate adversarial machine learning (ML) into standard red team exercises, testing for AI vulnerabilities proactively before deployment.
4. AI-Specific Incident Response:
   For the first time, formal incident response guidelines tailored to AI systems will be developed, providing a structured approach to AI-related security breaches. Expect to see playbooks developed for AI risks.
5. Advanced Threat Evolution:
   Fraud, misinformation, and network attacks will escalate as AI evolves across domains such as computer vision (CV), audio, and natural language processing (NLP). Expect to see attackers leveraging AI to increase both the speed and scale of attack, as well as semi-autonomous offensive models designed to aid in penetration testing and security research.
6. Emergence of AIPC (AI-Powered Cyberattacks):
   As hardware vendors capitalize on AI with advances in bespoke chipsets and tooling to power AI technology, expect to see attacks targeting AI-capable endpoints intensify, including:
   • Local model tampering. Hijacking models to abuse predictions, bypass refusals, and perform harmful actions.
   • Data poisoning.
   • Abuse of agentic systems. For example, prompt injections in emails and documents to exploit local models.
   • Exploitation of vulnerabilities in 3rd party AI libraries and models.

Recommendations for the Security Practitioner

In the 2024 threat report, we made several recommendations for organizations to consider that were similar in concept to existing security-related control practices but built specifically for AI, such as:  

1. Discovery and Asset Management: Identifying and cataloging AI systems and related assets.
2. Risk Assessment and Threat Modeling: Evaluating potential vulnerabilities and attack vectors specific to AI.
3. Data Security and Privacy: Ensuring robust protection for sensitive datasets.
4. Model Robustness and Validation: Strengthening models to withstand adversarial attacks and verifying their integrity.
5. Secure Development Practices: Embedding security throughout the AI development lifecycle.
6. Continuous Monitoring and Incident Response: Establishing proactive detection and response mechanisms for AI-related threats.

These practices remain foundational as organizations navigate the continuously unfolding AI threat landscape.

Building on these recommendations, 2024 marked a turning point in the AI landscape. The rapid AI 'electrification' of industries saw nearly every IT vendor integrate or expand AI capabilities, while service providers across sectors—from HR to law firms and accountants—widely adopted AI to enhance offerings and optimize operations. This made 2024 the year that AI-related third—and fourth-party risk issues became acutely apparent.  

During the Security for AI Council meeting at Black Hat this year, the subject of AI third-party risk arose. Everyone in the council acknowledged it was generally a struggle, with at least one member noting that a "requirement to notify before AI is used/embedded into a solution” clause was added in all vendor contracts. The council members who had already been asking vendors about their use of AI said those vendors didn’t have good answers. They “don't really know,” which is not only surprising but also a noted disappointment. The group acknowledged traditional security vendors were only slightly better than others, but overall, most vendors cannot respond adequately to AI risk questions. The council then collaborated to create a detailed set of AI 3rd party risk questions. We recommend you consider adding these key questions to your existing vendor evaluation processes going forward.   

1. Where did your model come from?
2. Do you scan your models for malicious code? How do you determine if the model is poisoned?
3. Do you log and monitor model interactions?
4. Do you detect, alert, and respond to mitigate risks that are identified in the OWASP LLM Top 10?
5. What is your threat model for AI-related attacks? Are your threat model and mitigations mapped or aligned to the MITRE Atlas?
6. What AI incident response policies does your organization have in place in the event of security incidents that impact the safety, privacy, or security of individuals or the function of the model?
7. Do you validate the integrity of the data presented by your AI system and/or model?

Remember that the security landscape—and AI technology—is dynamic and rapidly changing. It's crucial to stay informed about emerging threats and best practices. Regularly update and refine your AI-specific security program to address new challenges and vulnerabilities.  

And a note of caution. In many cases, responsible and ethical AI frameworks fall short of ensuring models are secure before they go into production and after an AI system is in use. They focus on things such as biases, appropriate use, and privacy.  While these are also required, don’t confuse these practices for security.