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%.

Topics

• Prompt injection and jailbreaks

Related items

• MediumVisual Studio Copilot and SSMS Remote Code Execution (CVE-2026-103572)Similar attack · Embrace The Red
• HighCVE-2026-110206: Roo Code command approval bypass in parseCommandLine() via command substitutionSimilar attack · NVD/CVE Database
• HighCVE-2026-110205: Roo Code command approval bypass through parseCommandLine() command substitutionSimilar attack · NVD/CVE Database
• HighCVE-2026-110204: Roo Code command approval bypass through parseCommandLine substitutionsSimilar attack · NVD/CVE Database
• HighCVE-2026-110203: Roo Code command approval bypass via quote-masking regexSimilar attack · NVD/CVE Database