local-debug
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate developer workflow for runtime debugging.\n- [DATA_EXPOSURE]: The instructions contain explicit safeguards against capturing sensitive data, stating: 'Never log secrets, tokens, auth headers, or full user PII. If a payload may contain them, log the shape (Object.keys(...)) or a redacted subset.'\n- [COMMAND_EXECUTION]: Codebase navigation uses standard LSP (Language Server Protocol) features like 'goToDefinition' and 'findReferences', which are expected behaviors for a coding-focused AI agent.\n- [DATA_EXFILTRATION]: No automated network exfiltration was detected. The skill relies on the user to manually 'paste the log output back here', keeping the user in control of what data is shared with the model.
Audit Metadata