security-review
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
scripts/dep-scan.cjsusingnodeto perform dependency scanning. This is a legitimate function for a security analysis tool. - [PROMPT_INJECTION]: The skill processes external data (repository code, PR diffs) which serves as a surface for indirect prompt injection. Malicious instructions embedded in the code being audited could potentially attempt to influence the agent's findings. * Ingestion points: Repository source code, pull request diffs, and default branch commits. * Boundary markers: None specified; the skill interprets raw code and diff data. * Capability inventory: The skill can execute local scripts and write results to the
.bug-hunter/directory. * Sanitization: No sanitization or input validation mechanisms are described for the analyzed content.
Audit Metadata