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
Risk Level
SAFE
Analyzed
Aug 28, 2026, 12:48 PM
Security Audit — agent-trust-hub — codebase-inspection