{"data":{"id":"59f32034-36f8-4365-a452-c80319596482","title":"Foundation AI in September: VLoc Bench and Cyber-Capability Safety","summary":"Foundation AI released VLoc Bench, a benchmark testing whether agents can localize vulnerable files in real repositories from only a CWE description and read-only access. The strongest of 27 evaluated models reaches only 0.229 File F1, and no model finds a correct file on 38.4% of tasks. A separate Safety-VLoc-Bench compares source code with stripped, decompiled binaries, where Antares-3B scores 0.823 File F1 on source but 0.000 on the attacker-oriented representation.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://blogs.cisco.com/ai/foundation-ai-in-september-vloc-bench-and-cyber-capability-safety/","publishedAt":"2026-10-06T22:00:44.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Antares-3B","Antares-1B","Antares-350M","VLoc Bench","Safety-VLoc-Bench"],"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":"2026-10-06T22:00:44.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}