code-documenter
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow incorporates validation steps that execute standard shell commands like 'python -m doctest', 'pytest', and 'npx @redocly/cli'. These are legitimate development tools used for documentation verification.
- [EXTERNAL_DOWNLOADS]: The skill references various documentation and linting tools such as 'redocly', 'pydocstyle', and 'linkchecker' that are typically installed via official registries like NPM and PyPI. These are recognized, well-known services.
- [INDIRECT_PROMPT_INJECTION]: The skill handles user-provided source code, creating an attack surface for indirect prompt injection. 1. Ingestion points: Source code files processed during analysis (SKILL.md). 2. Boundary markers: Not explicitly specified in the prompt templates. 3. Capability inventory: Validation commands such as python and npx (SKILL.md). 4. Sanitization: Relies on the agent's generative logic without explicit validation rules.
- [DYNAMIC_EXECUTION]: The use of 'doctest' and 'pytest' for validating code examples involves the dynamic execution of code snippets within documentation. This is a primary intended function of the skill for ensuring documentation accuracy and is considered safe within the context of developer tooling.
Audit Metadata