{"data":{"id":"cfaa28d0-ee56-4e90-bc92-841753d4f83e","title":"Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence","summary":"This research measures how LLM vulnerability auditors respond to static-analysis notes, using 916 PrimeVul function pairs, eleven model configurations and 16,572 audits. Fabricated assurances that a missing check exists lowered detection of real vulnerabilities by up to 19 points relative to true notes, while fabricated alarms rarely reduced accuracy. Verifying each claim in a separate call and showing the refuted claims raised accuracy under false assurances by 12 points in a pre-specified test (p=0.002), though the gain for a second model was smaller and not significant.","solution":"Pipelines should verify a tool's guarantees before the model relies on them, and studies should measure deference in a direction-aware way. Verifying each claim in a separate call and showing the refuted claims improved accuracy under false assurances in the pre-specified test.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.32876v1","publishedAt":"2026-10-23T16:45:10.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"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":"2026-10-23T16:45:10.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}