{"data":{"id":"7b58d8d9-d97a-4dff-a628-6de0a2abff78","title":"Replication of Agentic Security Events: Audit and Investigation (ROGUE-AI)","summary":"ROGUE-AI is a multi-agent framework that rebuilds reported LLM agent incidents offline, paired with a control lacking only the blamed cause. It reproduced the reported harm in 89% of 108 attempted replications, and agents built on five GPT, Claude, Gemini and DeepSeek models repeated the mistake in 18% to 33% of runs, versus at most 1% without the blamed cause. Of 72 incidents with real-world harm, 62 had no attacker, and agents missed ordinary hazards such as a database shared with the live site.","solution":"A warning after each tool output that names the hazard and its consequence lowered harm for all five models, whereas a same-length note that does not mention the hazard left most harm in place. The authors also suggest vendors rerun the ROGUE-AI replications as an audit before each new release.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.26553v1","publishedAt":"2026-11-19T18:23:35.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Anthropic","Google"],"affectedVendorsRaw":["GPT","Claude","Gemini","DeepSeek","Replit coding agent"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-19T18:23:35.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}