codebase-design
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided codebase information and module definitions to provide architectural advice and explore design alternatives.
- Ingestion points: User codebases, module interfaces, and technical briefs as described in
DESIGN-IT-TWICE.md. - Boundary markers: None explicitly defined within the skill instructions.
- Capability inventory: Use of the
Agenttool to spawn sub-agents for parallel design exploration as specified inDESIGN-IT-TWICE.md. - Sanitization: The skill does not implement specific sanitization or filtering for the code it analyzes, relying on the platform's underlying safety layers.
Audit Metadata