{"data":{"id":"bcd8fe95-efa2-4688-8ada-8db42ff3fd84","title":"Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks","summary":"Researchers introduce a benchmark for indirect prompt injection that tests task-tampering attacks, where planted content influences a decision the source is not authorized to make, rather than redirecting the agent's task. Across 90 validated cases in three tool-use environments and five LLMs, attacks on decision rules, available actions, and state had higher mean success than objective attacks without defense. A detection-and-removal defense cut objective-targeting attacks to 2.4% success but left observation- and state-targeting attacks at 9.5% and 12.1%, and a tool-policy defense still allowed 15.4% attack success.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.07640v1","publishedAt":"2026-11-05T08:25:27.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"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":"2026-11-05T08:25:27.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}