# Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

arXiv: https://arxiv.org/abs/2607.25379 · HTML: https://mlsanity.com/paper/2607.25379/

## Key facts

- Cited by 1 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 85 of its 93 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## 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 85)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models](https://mlsanity.com/paper/2406.10162/) (2024)
- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [Compute Trends Across Three Eras of Machine Learning](https://mlsanity.com/paper/2202.05924/) (2022)
- [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025)
- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models](https://mlsanity.com/paper/2312.04724/) (2023)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [LLM Agents can Autonomously Exploit One-day Vulnerabilities](https://mlsanity.com/paper/2404.08144/) (2024)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [Goal Misgeneralization in Deep Reinforcement Learning](https://mlsanity.com/paper/2105.14111/) (2021)
- [Optimal Policies Tend to Seek Power](https://mlsanity.com/paper/1912.01683/) (2019)
- [LLM Agents can Autonomously Hack Websites](https://mlsanity.com/paper/2402.06664/) (2024)
- [PentestGPT: An LLM-empowered Automatic Penetration Testing Tool](https://mlsanity.com/paper/2308.06782/) (2023)
- [CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities](https://mlsanity.com/paper/2503.17332/) (2025)
- [Teams of LLM Agents can Exploit Zero-Day Vulnerabilities](https://mlsanity.com/paper/2406.01637/) (2024)
- [NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security](https://mlsanity.com/paper/2406.05590/) (2024)
- [CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models](https://mlsanity.com/paper/2404.13161/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)](https://mlsanity.com/paper/2610.20437/) (2026)

## Abstract (arXiv)

Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable agent within the environments used to evaluate it. This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action. We use two separate preliminary incident records: the reported July 2026 Hugging Face/OpenAI evaluation breach and Anthropic's subsequent three-incident evaluation review. A comparative evidence protocol distinguishes record-specific factual claims from the shared systems lesson: the evaluation environment is itself part of the security boundary. Across the taxonomy and records, we examine controls for containment, privilege separation, provenance, and responder access, including the dual-use problem that defensive artifacts may also enable misuse. The review identifies practical priorities for evaluating cyber capability together with the security of the environment in which that capability is exercised.