prd-to-plan
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Product Requirements Documents (PRDs) and explores the local codebase, which presents an indirect injection surface.
- Ingestion points: The agent reads PRD content from the conversation history or user-specified files, and explores the existing codebase in the current directory.
- Boundary markers: The instructions do not specify any delimiters or safety markers (e.g., XML tags or block quotes) to isolate the untrusted PRD content from the agent's instructions.
- Capability inventory: The skill utilizes filesystem capabilities to explore directory structures, create new directories (
./docs/<feature-name>/), and write Markdown files (plan.md). - Sanitization: There is no evidence of sanitization or validation performed on the PRD content before it is used to generate the plan or determine the filesystem paths.
Audit Metadata