document
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code and component structures to generate documentation, representing an indirect prompt injection attack surface.
- Ingestion points: Source files, API endpoints, and database structures specified in arguments or identified via analysis (SKILL.md).
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions in the source data are defined.
- Capability inventory: Read, Grep, Write, Glob, and Bash tools used for analysis and documentation creation (SKILL.md).
- Sanitization: The skill instructions do not specify sanitization or validation of the code content before processing.
Audit Metadata