{"data":{"id":"2f52337b-c74c-4f07-a180-27b2749b32ed","title":"ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems","summary":"ErosionBench is a benchmark that tests whether multi-agent LLM systems drift into unsafe tool actions as benign requests propagate through poisoned shared state, long-context documents and trusted peer messages. It covers 1,728 scenarios across four enterprise domains, plus 198 image-based attacks paired with text equivalents. A proposed Meta-Auditor reaches 98.5% recall at a 2.9% false-positive rate on a held-out split, and its detection is channel-invariant across image and text attacks.","solution":"The source proposes a calibrated Meta-Auditor pairing synchronous state checks with asynchronous trajectory monitoring as a reference defense.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.11266v1","publishedAt":"2026-11-08T09:40:52.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Google","Anthropic"],"affectedVendorsRaw":["GPT","Gemini","Claude"],"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":"2026-11-08T09:40:52.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}