{"data":{"id":"b42a8ad1-72a0-4b6d-9003-306a827355e5","title":"Do Benign-Trained Hidden-State Probes Detect Tool Errors Under Adversarial Conditions?","summary":"This research asks whether hidden-state probes trained only on benign tool use still detect incorrect tool actions under adversarial conditions. The authors test three models (Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, GLM-4.6V-Flash) on four AgentDojo suites across benign, prompt-injection, system-override and tool-poisoning conditions, comparing the probes with three scalar uncertainty metrics. Under the system-override condition with Qwen2.5-14B-Instruct, all three uncertainty metrics beat the probe on AUROC and average precision in six significant paired tests after Holm correction, so the authors conclude benign-trained probes should not be assumed reliable for this purpose.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.11172v1","publishedAt":"2026-11-08T06:27:15.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen2.5-7B-Instruct","Qwen2.5-14B-Instruct","GLM-4.6V-Flash"],"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":"2026-11-08T06:27:15.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}