documentation-generation-doc-generate
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to extract and process information from repository files, including comments and docstrings, which are untrusted inputs.
- Ingestion points: As specified in SKILL.md, the agent extracts data from "code, configs, and comments."
- Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore potential injection attempts within the extracted comments.
- Capability inventory: The skill has the capability to read files and write documentation artifacts. It is also instructed to "run existing schema/doc builds," which involves command execution.
- Sanitization: There is no explicit sanitization step for comment content before it is processed by the LLM for documentation generation.
- [COMMAND_EXECUTION]: The documentation templates and worked examples involve executing shell commands and scripts.
- Evidence: SKILL.md instructs the agent to "run the existing schema/doc build and the documented read-only call against a test fixture." Additionally, resources/implementation-playbook.md contains README templates with commands like "pip install" and "git clone".
Audit Metadata