{"data":{"id":"2e5e83d5-c708-4dc3-86ad-6cd185f37a88","title":"Towards Safe Autonomy for Computer Use","summary":"SA-CUA is a dual-LLM framework for Computer Use Agents, which act visually on screens and lack a boundary between trusted and untrusted content. It derives conservative deterministic rules from the accessibility tree to unmask trusted regions from the privileged LLM's screenshot, and uses an endorsement channel to verify untrusted values before they reach the trusted domain. The authors report it keeps much higher utility than CaMeL-CUA while holding the attack success rate at zero.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.18508v1","publishedAt":"2026-10-13T15:03:33.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLM-based computer use agents","CaMeL-CUA"],"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":"2026-10-13T15:03:33.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}