{"data":{"id":"57a35230-0214-4315-a42a-109bb646b49b","title":"SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection","summary":"SPILLWAY is a defense for tool-using agents against prompt injection that checks where an action's target comes from. It admits a call when each target value absent from the user's task was returned by a read-only tool in a typed field, or is covered by a fixed delegation rule, instead of relying on a language model's judgment. Across three backbones and seven task suites on one of them, no standard templated injection redirected an action to an attacker's target under SPILLWAY.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.07222v1","publishedAt":"2026-11-04T23:18:10.000Z","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":"2026-11-04T23:18:10.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","confidentiality"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}