skills/promptdriven/pdd/pdd-product/Gen Agent Trust Hub

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 create and then processed by the pdd workflow run product command.
  • 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 the gh CLI.
  • 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
Risk Level
SAFE
Analyzed
Nov 21, 2026, 03:21 AM