code-documenter

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to validate documentation and test code examples.
  • Evidence: SKILL.md specifies the use of python -m doctest, pytest --doctest-modules, tsc --noEmit, and npx @redocly/cli during the validation workflow step.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of standard documentation and linting tools from official package registries.
  • Evidence: Reference files suggest installing packages such as pydocstyle, interrogate, linkchecker, broken-link-checker, and eslint-plugin-jsdoc using pip and npm.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to its core functionality of executing code examples found in source files.
  • Ingestion points: The agent reads and processes external source code and documentation files to generate and validate docstrings (SKILL.md).
  • Boundary markers: None provided to separate untrusted code data from agent instructions.
  • Capability inventory: The skill executes shell commands (e.g., doctest, pytest) to verify code examples found within the ingested documentation.
  • Sanitization: No mechanisms for sandboxing or sanitizing code examples are described before they are passed to execution tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 09:32 AM
Security Audit — agent-trust-hub — code-documenter