documentation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from a codebase (such as source code comments, API definitions, and git history) to generate technical documentation, which introduces a surface for indirect prompt injection.
- Ingestion points: Source code files, API endpoint definitions, and commit history as specified in Phases 2, 4, and 7.
- Boundary markers: The provided prompts do not specify the use of delimiters or warnings to ignore instructions embedded in the processed data.
- Capability inventory: The workflow orchestrates multiple external skills (e.g.,
@api-documenter,@changelog-automation) that typically possess file read and write capabilities. - Sanitization: The instructions do not define any sanitization, escaping, or validation steps for the content being extracted and documented.
Audit Metadata