# A New Framework for Cybersecurity Refusals in AI Agents

arXiv: https://arxiv.org/abs/2606.02644 · HTML: https://mlsanity.com/paper/2606.02644/

## 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 26 of its 42 references that are in the map.
- First posted on arXiv 31 May 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, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models](https://mlsanity.com/paper/2308.01263/) (2023)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [OR-Bench: An Over-Refusal Benchmark for Large Language Models](https://mlsanity.com/paper/2405.20947/) (2024)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents](https://mlsanity.com/paper/2506.14866/) (2025)
- [SafeArena: Evaluating the Safety of Autonomous Web Agents](https://mlsanity.com/paper/2503.04957/) (2025)
- [CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities](https://mlsanity.com/paper/2503.17332/) (2025)
- [NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security](https://mlsanity.com/paper/2406.05590/) (2024)
- [Does Refusal Training in LLMs Generalize to the Past Tense?](https://mlsanity.com/paper/2407.11969/) (2024)
- [CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale](https://mlsanity.com/paper/2506.02548/) (2025)
- [Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks](https://mlsanity.com/paper/2501.16466/) (2025)
- [Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing](https://mlsanity.com/paper/2512.09882/) (2025)
- [Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing](https://mlsanity.com/paper/2509.09207/) (2025)
- [PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities](https://mlsanity.com/paper/2510.11688/) (2025)
- [Evaluating AI cyber capabilities with crowdsourced elicitation](https://mlsanity.com/paper/2505.19915/) (2025)

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

- [Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response](https://mlsanity.com/paper/2607.25379/) (2026)

## Abstract (arXiv)

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existing benchmarks for AI agents in cybersecurity focus mainly on measuring proficiency--how effectively agents can complete offensive security tasks--but neglect a critical question: when and how should agents refuse harmful requests? We present the first framework for establishing refusal boundaries in offensive security contexts. Our framework defines (1) principled criteria for when tasks should be refused, (2) categories of tasks that warrant refusal, and (3) evaluation methodology for measuring agent robustness under both benign and adversarial conditions. We apply this framework to assess how current LLM-powered agents adhere to appropriate refusal boundaries across a range of web-based offensive security scenarios, finding that 6 of 8 frontier models tested show near-zero refusal rates, with only 2 models (GPT-5.2 and GPT-5.1 Codex) demonstrating any meaningful refusal behavior.