codebase-inspection
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the pygount package from the standard PyPI registry using pip.
- [COMMAND_EXECUTION]: The skill utilizes shell commands to navigate the filesystem, execute the pygount CLI, and process output with standard utilities like sort and head.
- [INDIRECT_PROMPT_INJECTION]: The skill processes contents of local repositories to generate metrics. 1. Ingestion points: Local repository files analyzed by the pygount command. 2. Boundary markers: The skill specifies structured output formats (summary and JSON) to separate tool output from instructions. 3. Capability inventory: Package installation via pip and subprocess execution of the analysis tool. 4. Sanitization: The tool summarizes file content into numeric metrics and language classifications, which limits the risk of raw file content influencing the agent's behavior.
Audit Metadata