{"data":{"id":"dc4c33ee-8345-4b04-a8b2-569bc079ed48","title":"SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments","summary":"SentryBench is a benchmark for LLM agents that call consequential public-safety tools, such as public alerts, responder dispatch and citizen-record queries. It scores attack success, over-refusal and over-reaction together with an asymmetric cost functional, using scenarios drawn from real emergency-call transcripts, disaster messages and injection/jailbreak payloads. Across 840 scored episodes on three frontier models and three defenses, refuse-more caution pushed over-refusal to 100 percent on two models for at most a 3.7-point change in attack success, while the trust-gating wrapper gave the lowest harm on every model.","solution":"The source proposes a targeted trust-gating wrapper as a defense, which it reports has the lowest harm on every model, over-refusal at or below baseline, and higher containment. It does not give a deployment fix beyond this defense. It also notes that provider content filters perform part of the defending and must be reported separately.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.34535v1","publishedAt":"2026-10-25T19:49:40.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","jailbreak"],"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":"2026-10-25T19:49:40.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","availability","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051","AML.T0054"]}}