api-documenter
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes implementation code, schemas, and examples, which are untrusted data sources that could be used for indirect prompt injection.
- Ingestion points: The skill analyzes 'real implementation, schema, and examples' (SKILL.md).
- Boundary markers: No delimiters or 'ignore' instructions for embedded content are defined in the working mode.
- Capability inventory: The skill has 'workspace-write' permissions, allowing it to generate or modify documentation files in the environment.
- Sanitization: No specific input sanitization, filtering, or escaping logic is described in the quality checks or instructions.
Audit Metadata