pdd-product
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from GitHub issue bodies to generate product roadmaps, plan files, and feature issues. This represents an attack surface where a malicious user could embed instructions in a product request to influence the agent's behavior.
- Ingestion points: The initial product request is captured via
gh issue createand then processed by thepdd workflow run productcommand. - Boundary markers: The instructions lack specific delimiters or directions for the agent to treat the issue content as untrusted data, increasing the risk of the agent obeying instructions embedded within the request.
- Capability inventory: The skill is capable of performing file writes (creating
product/map.md,product/plan.md, and contract files) and managing GitHub issues through theghCLI. - Sanitization: No input sanitization or validation logic is specified to filter the product request content before it is interpolated into the workflow's context.
Audit Metadata