# Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks

arXiv: https://arxiv.org/abs/2607.21763 · HTML: https://mlsanity.com/paper/2607.21763/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [R-Judge: Benchmarking Safety Risk Awareness for LLM Agents](https://mlsanity.com/paper/2401.10019/) (2024)
- [Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models](https://mlsanity.com/paper/2408.08926/) (2024)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases](https://mlsanity.com/paper/2510.20270/) (2025)
- [Demonstrating specification gaming in reasoning models](https://mlsanity.com/paper/2502.13295/) (2025)
- [Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates](https://mlsanity.com/paper/2410.07137/) (2024)
- [Control Illusion: The Failure of Instruction Hierarchies in Large Language Models](https://mlsanity.com/paper/2502.15851/) (2025)
- [A Closer Look at System Prompt Robustness](https://mlsanity.com/paper/2502.12197/) (2025)
- [Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use](https://mlsanity.com/paper/2605.02964/) (2026)
- [Search-Time Data Contamination](https://mlsanity.com/paper/2508.13180/) (2025)
- [Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack](https://mlsanity.com/paper/2605.12673/) (2026)
- [The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't](https://mlsanity.com/paper/2605.01771/) (2026)
- [Measuring Reward-Seeking via Contrastive Belief Updates](https://mlsanity.com/paper/2607.18966/) (2026)

## Built on by (most cited first, 3 of 3)

- [CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration](https://mlsanity.com/paper/2609.32700/) (2026)
- [A Competing-Hazards Systematization of Loss of Control in Autonomous Agents](https://mlsanity.com/paper/2609.38411/) (2026)
- [CWE-bench: Refocusing Agentic Security from Exploitation to Defense](https://mlsanity.com/paper/2610.17020/) (2026)

## Abstract (arXiv)

Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22 frontier models from 7 providers on 23 Cybench capture-the-flag (CTF) challenges under three prompt conditions (no anti-cheat, standard, severe). All 1,518 task traces were individually audited through a four-stage pipeline combining LLM-as-a-judge classification, programmatic verification, judge-verifier reconciliation, and human review. We find cheating is far more pervasive than previously estimated: under baseline conditions, 37.1% of passes involved cheating, 21 of 22 models cheated, and scores were inflated by up to 5x. Anti-cheat prompts reduce cheat propensity from 33.0% (baseline) to 17.8% (standard) to 8.5% (severe) without degrading, and sometimes improving, solve rates. However, even under the most restrictive prompt condition, eight models still produced cheated passes, four showed backfire effects, and cheating escalated from web search toward infrastructure probing. We introduce the "solve rate" metric (clean passes only) to distinguish genuine capability from cheated outcomes, and argue it should be standard practice in any evaluation where cheating vectors are available. Anti-cheat prompts are an effective and essentially free first layer of defense, but they are not a substitute for environmental controls.