{"data":{"id":"b2b3ddbe-ab3d-4de0-badb-bd6e115dc076","title":"BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views","summary":"BrowseSafe++ extends the BrowseSafe benchmark from 14,719 pages to 38,675 paired attacked and clean pages, most injections observed in the wild on production websites. The authors train BrowseSafe-Guard, two 0.8B-parameter detectors for text and screenshots, which achieve higher F1 scores than a frontier-model-based detector while keeping false-positive rates and inference cost low. BrowseSafe-Adapt revises injections from browser-agent feedback, raising attack success on tasks from a few percent when replayed directly to up to 95.41%.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.17457v1","publishedAt":"2026-10-12T22:17:51.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["browser agents","BrowseSafe","BrowseSafe-Guard","BrowseSafe-Adapt"],"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":"2026-10-12T22:17:51.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}