literate-guide
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the codebase to generate narrative documentation.
- Ingestion points: Step 2 (Deep Reading) instructs the agent to read source code, README files, documentation, comments, commit messages, issue trackers, and git log output.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded in the codebase data.
- Capability inventory: The skill utilizes file system read and write operations, and instructions imply the use of version control tools to analyze project history.
- Sanitization: No sanitization or validation logic is specified for the data read from the codebase before it is processed by the agent.
Audit Metadata