{"data":{"id":"39dcbcef-ea8e-4634-9115-99e09fb97b01","title":"How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery","summary":"Researchers tested 24 model-runner configurations of an open-source agent harness on a production codebase with non-public vulnerabilities, across 265 confirmed security root causes. The largest two-run configuration covered 60.4% of findings, and 14.3% were found by exactly one model. In a four-model experiment, an engineered prompt with CodeQL-derived call-graph context raised criticality-weighted yield by 20-86% for smaller and mid-tier models, versus 2% for the frontier model.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.28802v1","publishedAt":"2026-10-20T18:25:47.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"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":"2026-10-20T18:25:47.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}