{"data":{"id":"c02d123c-bf82-4cfb-8be0-6705fe7dc925","title":"Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning","summary":"This paper studies parameter poisoning in LLM agents, where an indirect prompt injection keeps the intended action but manipulates a tool argument such as a recipient. The authors propose AuthorityFlow, a three-stage defense that builds a task-specific trust hierarchy from the user query, traces each argument to its supporting information field, and flags low-trust influence. On their FactAuthBench evaluation, attack success falls from 93.06% to 9.03%, with 82.64% benign task utility retained versus 90.28% without defense.","solution":"AuthorityFlow: a three-stage parameter-level defense that constructs a task-specific trust hierarchy over information fields, traces each tool argument to its supporting field, and accepts a value only when that field is trusted to determine the parameter under the current task.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.04673v1","publishedAt":"2026-11-03T10:57:12.000Z","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":"2026-11-03T10:57:12.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}