{"data":{"id":"797a40af-08db-4b98-9e69-11713f004776","title":"The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection","summary":"This research studies prompt injection against medical multi-agent systems, where LLM agents discuss a clinical case. Across two systems, two model families and three benchmarks, a single injected passage succeeds in up to 61% of cases, and collaboration does not consistently protect against it. The authors propose a training-free defense that separates patient findings from clinical judgments and checks each judgment against the findings alone, lowering attack success on MedQA to 4-7% while keeping accuracy on clean cases.","solution":"The authors propose a training-free defense that verifies the clinical judgments behind the system's decision: it separates the patient's findings from clinical judgments (diagnoses, recommendations and instructions) and checks each judgment against the findings alone, so the decision rests only on supported judgments.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.22594v1","publishedAt":"2026-10-15T19:43:57.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-10-15T19:43:57.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}