cy-create-prd

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes content from user-provided _idea.md files, existing _prd.md files, and codebase search results (SKILL.md, Step 1 and 2).
  • Ingestion points: External data enters the context through direct file reads and codebase pattern matching during the discovery phase.
  • Boundary markers: The skill does not define explicit delimiters or 'ignore' instructions for the agent when processing ingested data to separate it from core instructions.
  • Capability inventory: The skill is capable of directory creation, file writing to the .compozy/tasks/ path, and performing web research via agent search tools (SKILL.md, Step 2, 4, 5, and 7).
  • Sanitization: Content from context files is synthesized directly into the final PRD draft without automated sanitization or validation logic, relying on manual user oversight.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:15 AM