jb-browser-testing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains instructional content for browser automation and testing. No malicious code, obfuscation, or injection attempts were detected.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill promotes security best practices by explicitly instructing the agent to never place passwords, cookies, tokens, or exported state contents in commands, chat, repository files, or commits.
- [EXTERNAL_DOWNLOADS]: The skill references Vercel's agent-browser and the author-aligned jb-chrome-mcp tool. These references are for documentation and usage purposes and do not involve unverified or high-risk remote code execution.
Audit Metadata