prd-to-plan
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs expected file system operations related to codebase analysis and plan generation within the project directory.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Product Requirement Documents (PRDs) as input.
- Ingestion points: External PRD content provided via user input or context (SKILL.md).
- Boundary markers: None identified; instructions in the PRD are not explicitly isolated from the agent's system prompt.
- Capability inventory: Performs read operations on the codebase to understand architecture and write operations to save plans in the
./plans/directory. - Sanitization: No validation or escaping of PRD content is performed before processing.
Audit Metadata