uw-complete
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from documentation gap reports and source code files, which can serve as a vector for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill reads data from 'docs/unwind/layers/{layer}/gaps.md' and source code files (e.g., 'src/schema.ts') to determine documentation tasks.
- Boundary markers: The instructions for the sub-agents lack explicit delimiters or safety instructions to distinguish between documentation content and agent commands.
- Capability inventory: The skill is permitted to 'Write' and 'Edit' within the 'docs/unwind/**' directory and can dispatch additional 'Task' sub-agents.
- Sanitization: The skill does not perform validation or sanitization on the text extracted from source files before passing it to sub-agents for processing.
Audit Metadata