{"data":{"id":"50182ab4-3210-48f8-8057-ba2b767bd447","title":"DEPUTYBENCH: Evaluating Contextual Safety in Enterprise Agents","summary":"DEPUTYBENCH is an executable benchmark of 375 instances from 79 base items for testing whether enterprise agents respect organizational permissions while completing legitimate work. Across 12 models it reports 88.0% pooled safety and 79.1% paired success. In a controlled study of 27 matched tasks, restricted execution occurred more often with missing evidence (10.3%) than with explicit non-permission (3.5%), a 6.8-percentage-point difference.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.13355v1","publishedAt":"2026-11-09T23:26:40.000Z","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":"2026-11-09T23:26:40.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}