git-doc-updater

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs command execution by running a local Python script scripts/count_mcp_tools.py via the uv package manager. This action is explicitly documented as a required step for synchronizing tool lists in the project documentation.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests and processes untrusted data from code changes and commit messages to generate documentation content.
  • Ingestion points: Git commit messages and source code diffs analyzed during the execution flow.
  • Boundary markers: No specific delimiters are defined to separate code data from the agent's internal instructions.
  • Capability inventory: The skill can write to various Markdown files (README.md, CHANGELOG.md, etc.) and execute local Python scripts.
  • Sanitization: The instructions do not describe a process for sanitizing or escaping content derived from code changes before it is written to documentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:34 AM
Security Audit — agent-trust-hub — git-doc-updater