{"data":{"id":"2678e4bf-008e-4086-af6c-830a5f164149","title":"SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models","summary":"SkillScreen is a compact decision model that scores whether an agent skill is malicious directly from its SKILL.md file in a single forward pass. On MaliciousSkillBench it reaches 99% recall on unseen attack families while flagging 20-25% of benign skills, fewer than the word-level classifier and prompted LLM judges tested. It also generalizes better than a fully fine-tuned encoder to unseen sources, though unfamiliar benign sources sharply raise false positives.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.17727v1","publishedAt":"2026-10-13T05:03:43.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["supply_chain"],"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":"2026-10-13T05:03:43.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":["AML.T0010"]}}