lcs-toprd
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from various local files which could contain untrusted instructions. However, its capabilities are restricted to document generation and local state updates.
- Ingestion points: explore.md, intent.md, debug.md, research/, wayfinder-map.md, and direct user input.
- Boundary markers: None explicitly defined in the skill body; it refers to external safety rules.
- Capability inventory: File read and file write restricted to the workspace work-item directory.
- Sanitization: Not present.
Audit Metadata