# OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety

arXiv: https://arxiv.org/abs/2507.06134 · HTML: https://mlsanity.com/paper/2507.06134/

## Key facts

- Cited by 75 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 42 of its 56 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Placed in

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

## Builds on (most cited first, 30 of 42)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (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)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)
- [SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models](https://mlsanity.com/paper/2402.05044/) (2024)
- [WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models](https://mlsanity.com/paper/2406.18510/) (2024)
- [PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action](https://mlsanity.com/paper/2409.00138/) (2024)
- [ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning](https://mlsanity.com/paper/2503.22738/) (2025)
- [ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents](https://mlsanity.com/paper/2410.06703/) (2024)
- [Dissecting Adversarial Robustness of Multimodal LM Agents](https://mlsanity.com/paper/2406.12814/) (2024)
- [Attacking Vision-Language Computer Agents via Pop-ups](https://mlsanity.com/paper/2411.02391/) (2024)
- [SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents](https://mlsanity.com/paper/2412.13178/) (2024)
- [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)
- [ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming](https://mlsanity.com/paper/2404.08676/) (2024)
- [RedCode: Risky Code Execution and Generation Benchmark for Code Agents](https://mlsanity.com/paper/2411.07781/) (2024)
- [SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety](https://mlsanity.com/paper/2404.05399/) (2024)
- [SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models](https://mlsanity.com/paper/2410.18927/) (2024)
- [Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents](https://mlsanity.com/paper/2410.13886/) (2024)
- [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://mlsanity.com/paper/2412.15701/) (2024)
- [SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types](https://mlsanity.com/paper/2410.21965/) (2024)

## Built on by (most cited first, 30 of 75)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Training Proactive and Personalized LLM Agents](https://mlsanity.com/paper/2511.02208/) (2025)
- [Magentic-UI: Towards Human-in-the-loop Agentic Systems](https://mlsanity.com/paper/2507.22358/) (2025)
- [From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents](https://mlsanity.com/paper/2606.04990/) (2026)
- [Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents](https://mlsanity.com/paper/2602.13379/) (2026)
- [The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems](https://mlsanity.com/paper/2602.17753/) (2026)
- [Building a Foundational Guardrail for General Agentic Systems via Synthetic Data](https://mlsanity.com/paper/2510.09781/) (2025)
- [Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges](https://mlsanity.com/paper/2510.23883/) (2025)
- [Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw](https://mlsanity.com/paper/2604.04759/) (2026)
- [OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows](https://mlsanity.com/paper/2510.24411/) (2025)
- [Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents](https://mlsanity.com/paper/2607.10487/) (2026)
- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)
- [SafePro: Evaluating the Safety of Professional-Level AI Agents](https://mlsanity.com/paper/2601.06663/) (2026)
- [LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios](https://mlsanity.com/paper/2602.03255/) (2026)
- [STAC: When Innocent Tools Form Dangerous Chains for LLM Agents](https://mlsanity.com/paper/2509.25624/) (2025)
- [Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2606.10749/) (2026)
- [Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification](https://mlsanity.com/paper/2607.01793/) (2026)
- [MASEval: Extending Multi-Agent Evaluation from Models to Systems](https://mlsanity.com/paper/2603.08835/) (2026)
- [How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation](https://mlsanity.com/paper/2606.16821/) (2026)
- [SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning](https://mlsanity.com/paper/2510.26037/) (2025)
- [SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do](https://mlsanity.com/paper/2603.27148/) (2026)
- [Proof-of-Guardrail in AI Agents and What (Not) to Trust from It](https://mlsanity.com/paper/2603.05786/) (2026)
- [BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments](https://mlsanity.com/paper/2603.25747/) (2026)
- [WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections](https://mlsanity.com/paper/2605.15030/) (2026)
- [Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents](https://mlsanity.com/paper/2605.16282/) (2026)
- [DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses](https://mlsanity.com/paper/2512.02282/) (2025)
- [ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation](https://mlsanity.com/paper/2603.18762/) (2026)
- [Preference Redirection via Attention Concentration: An Attack on Computer Use Agents](https://mlsanity.com/paper/2604.08005/) (2026)
- [MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents](https://mlsanity.com/paper/2605.03952/) (2026)
- [LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection](https://mlsanity.com/paper/2605.17986/) (2026)

## Abstract (arXiv)

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While prior benchmarks have attempted to assess agent safety, most fall short by relying on simulated environments, narrow task domains, or unrealistic tool abstractions. We introduce OpenAgentSafety, a comprehensive and modular framework for evaluating agent behavior across eight critical risk categories. Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms; and supports over 350 multi-turn, multi-user tasks spanning both benign and adversarial user intents. OpenAgentSafety is designed for extensibility, allowing researchers to add tools, tasks, websites, and adversarial strategies with minimal effort. It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors. Empirical analysis of five prominent LLMs in agentic scenarios reveals unsafe behavior in 51.2% of safety-vulnerable tasks with Claude-Sonnet-3.7, to 72.7% with o3-mini, highlighting critical safety vulnerabilities and the need for stronger safeguards before real-world deployment.