review
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate development tool that provides a structured and secure workflow for reviewing code and plans. No malicious patterns or security risks were found during analysis.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard development commands, including git operations (status, diff, log) and code quality tools (ruff, black, mypy, pytest). These commands are used appropriately for project inspection and validation.
- [PROMPT_INJECTION]: The skill ingests untrusted data from local files, including code diffs and documentation files (TODOS.md, CLAUDE.md). This ingestion, combined with shell access via the Bash tool for running development utilities (git, ruff, pytest), creates a surface for indirect prompt injection. The skill manages this risk using a structured multi-phase workflow (CEO, Design, Engineering) that acts as a set of boundary markers; however, no explicit sanitization of file content was observed.
- [EXTERNAL_DOWNLOADS]: References to external sites are limited to the vendor's official GitHub repository for documentation and installation. No unauthorized downloads or remote script executions were detected.
Audit Metadata