code-documenter

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run shell commands to validate documentation and code examples, such as python -m doctest, pytest, and tsc --noEmit. (SKILL.md)\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing and using third-party tools and libraries from public registries, including eslint-plugin-jsdoc, pydocstyle, and interrogate. (references/coverage-reports.md)\n- [REMOTE_CODE_EXECUTION]: The core workflow uses npx to dynamically download and execute the @redocly/cli tool for linting OpenAPI specifications. (SKILL.md)\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it executes automated tests on user-provided source files. Malicious code embedded in docstrings or documentation examples could be executed during the validation phase. (SKILL.md)\n
  • Ingestion points: User-provided source code files and API specifications.\n
  • Boundary markers: None identified for isolating documentation examples during testing.\n
  • Capability inventory: Ability to execute shell commands (python, npx, pytest).\n
  • Sanitization: No validation or sanitization is performed on code examples before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 07:57 AM
Security Audit — agent-trust-hub — code-documenter