{"data":{"id":"1e758243-24cd-4509-9044-40a7f14d2f1e","title":"DISARM: Taint-gated counterfactual auditing for efficient defense against indirect prompt injection","summary":"DISARM is a training-free defense against indirect prompt injection in LLM agents, mediating actions at the tool boundary between internal planning and external tool execution. On AgentDojo with GPT-4o, it reduces the four-attack average attack success rate from 23.01% to 0.37% and raises utility under attack from 63.69% to 73.63%, at 4.29s benign latency. The authors note that semantic parameter pollution still retains 1.11% ASR, exposing limits of cue-based gating.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://doi.org/10.1177/0926227x261505043","publishedAt":"2026-11-04T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["GPT-4o"],"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":"2026-11-04T00:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality","integrity","availability"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0051"]}}