uw-analyze-domain
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data by reading codebase files (e.g., Java and TypeScript source files) to extract domain entities, business rules, and validation logic.
- Ingestion points: The skill instructions direct the agent to find and read entity classes, value objects, and validation files using
Read,Grep, andGlobtools. - Boundary markers: The instructions do not define specific delimiters or security headers to prevent the agent from following instructions that might be embedded within the source code being analyzed.
- Capability inventory: The skill possesses the ability to read project files, execute directory-level bash commands (
mkdir,ls), and write documentation to the local filesystem within thedocs/unwind/path. - Sanitization: No evidence of sanitization, filtering, or escaping of the content extracted from source files is present before it is interpolated into the generated documentation.
Audit Metadata