api-doc-writing
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of text-based instructions and templates for API documentation. It does not contain any scripts, binary files, or external network dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted inputs such as source code and specifications to generate documentation.
- Ingestion points: The workflow involves reading external code, specs, tests, and schemas (SKILL.md).
- Boundary markers: No explicit boundary markers or delimiters for the ingested data are specified.
- Capability inventory: The skill has no file writing, network access, or command execution capabilities.
- Sanitization: No input sanitization is mentioned, though safety rules explicitly warn against exposing secrets or inventing data.
Audit Metadata