SourcesAgents of Chaos Red Team Study — 16 Incidents 6 Agents 14 DaysAgents of Chaos·high signalSystematic red team study documenting 16 incidents across 6 autonomous coding agents over 14 days. Catalogues real-world failure modes.SourceSource pageAgents of Chaos↳ Follow the threadPolicy dependency / Stack layerCynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write PermissionsIT Security NewsStack layer / Update threadSLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill FilesarXivPolicy dependency / Stack layerCodenotary ships AgentMon 3 for agent runtime policy and compliance loggingAI Agent StoreStack layer / Threat pattern'Friendly Fire': AI Now PoC Tricks Claude Code and Codex Into Running README-Planted MalwareAI Now Institute (via The Hacker News)Stack layer / ContrastLong-Horizon-Terminal-Bench: Best Frontier Agent Clears Just 15% of Real Terminal Tasks, Mean 4.3%arXiv (Tencent Hunyuan) / HuggingFace Daily PapersStack layer / Update threadclaude-video Turns 'Watch This Video' Into a Portable Agent Skill — 8K Stars in WeeksGitHubThreat patternWitnessAI briefs enterprises on seven early agentic-AI security incidentsAI Agent StoreStack layer'Coding Agents Think Ahead of Time': Latent Probes Predict Outcomes 25 Steps EarlyarXiv / Hacker News