# AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

arXiv: https://arxiv.org/abs/2410.09024 · HTML: https://mlsanity.com/paper/2410.09024/

## Key facts

- Cited by 437 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 30 of 33)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet](https://mlsanity.com/paper/2408.15221/) (2024)
- [AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents](https://mlsanity.com/paper/2406.13352/) (2024)
- [Emergent autonomous scientific research capabilities of large language models](https://mlsanity.com/paper/2304.05332/) (2023)
- [GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning](https://mlsanity.com/paper/2406.09187/) (2024)
- [Evil Geniuses: Delving into the Safety of LLM-based Agents](https://mlsanity.com/paper/2311.11855/) (2023)
- [Evaluating Language-Model Agents on Realistic Autonomous Tasks](https://mlsanity.com/paper/2312.11671/) (2023)
- [Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification](https://mlsanity.com/paper/2407.20859/) (2024)
- [Calibrating LLM-Based Evaluator](https://mlsanity.com/paper/2309.13308/) (2023)
- [PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails](https://mlsanity.com/paper/2402.15911/) (2024)
- [Exploiting Novel GPT-4 APIs](https://mlsanity.com/paper/2312.14302/) (2023)
- [The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models](https://mlsanity.com/paper/2407.17915/) (2024)

## Built on by (most cited first, 30 of 437)

- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Survey on Evaluation of LLM-based Agents](https://mlsanity.com/paper/2503.16416/) (2025)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [Evaluation and Benchmarking of LLM Agents: A Survey](https://mlsanity.com/paper/2507.21504/) (2025)
- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [Large Language Models Often Know When They Are Being Evaluated](https://mlsanity.com/paper/2505.23836/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents](https://mlsanity.com/paper/2506.14866/) (2025)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [SafeArena: Evaluating the Safety of Autonomous Web Agents](https://mlsanity.com/paper/2503.04957/) (2025)
- [A Survey on Trustworthy LLM Agents: Threats and Countermeasures](https://mlsanity.com/paper/2503.09648/) (2025)
- [Steering Language Model Refusal with Sparse Autoencoders](https://mlsanity.com/paper/2411.11296/) (2024)
- [The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1](https://mlsanity.com/paper/2502.12659/) (2025)
- [AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents](https://mlsanity.com/paper/2503.09780/) (2025)
- [OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety](https://mlsanity.com/paper/2507.06134/) (2025)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems](https://mlsanity.com/paper/2502.11127/) (2025)
- [Multi-Agent Systems Execute Arbitrary Malicious Code](https://mlsanity.com/paper/2503.12188/) (2025)
- [MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control](https://mlsanity.com/paper/2410.17520/) (2024)
- [Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks](https://mlsanity.com/paper/2502.08586/) (2025)
- [RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments](https://mlsanity.com/paper/2505.21936/) (2025)
- [AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations](https://mlsanity.com/paper/2603.10749/) (2026)
- [WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation](https://mlsanity.com/paper/2605.10912/) (2026)
- [RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents](https://mlsanity.com/paper/2506.00618/) (2025)
- [Probing and Steering Evaluation Awareness of Language Models](https://mlsanity.com/paper/2507.01786/) (2025)
- [Fara-7B: An Efficient Agentic Model for Computer Use](https://mlsanity.com/paper/2511.19663/) (2025)
- [Towards Trustworthy GUI Agents: A Survey](https://mlsanity.com/paper/2503.23434/) (2025)
- [Enforcing Temporal Constraints for LLM Agents](https://mlsanity.com/paper/2512.23738/) (2025)

## Abstract (arXiv)

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external tools and can execute multi-stage tasks -- may pose a greater risk if misused, but their robustness remains underexplored. To facilitate research on LLM agent misuse, we propose a new benchmark called AgentHarm. The benchmark includes a diverse set of 110 explicitly malicious agent tasks (440 with augmentations), covering 11 harm categories including fraud, cybercrime, and harassment. In addition to measuring whether models refuse harmful agentic requests, scoring well on AgentHarm requires jailbroken agents to maintain their capabilities following an attack to complete a multi-step task. We evaluate a range of leading LLMs, and find (1) leading LLMs are surprisingly compliant with malicious agent requests without jailbreaking, (2) simple universal jailbreak templates can be adapted to effectively jailbreak agents, and (3) these jailbreaks enable coherent and malicious multi-step agent behavior and retain model capabilities. To enable simple and reliable evaluation of attacks and defenses for LLM-based agents, we publicly release AgentHarm at https://huggingface.co/datasets/ai-safety-institute/AgentHarm.