{"data":{"id":"ea289f05-2c97-4aca-9db2-e43e6969bb6e","title":"After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents","summary":"The authors introduce CarryoverBench, a benchmark of 12 personal-assistant scenarios and 101 attack tasks that tests indirect prompt injections persisting through memory files and scheduled tasks across sessions. Across five frontier models, planted payloads re-fire without measurable decay over five rounds, and conditional on successful planting, the trigger stage often adds little protection. Porting the Latent channel to the Hermes runtime attenuates but does not eliminate the effect.","solution":"The source suggests that carryover defense requires runtime-layer controls in addition to prompt-level interventions.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.28425v1","publishedAt":"2026-10-20T15:55:05.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLM agents","Hermes"],"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":"2026-10-20T15:55:05.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}