prd-to-issues
Warn
Audited by Snyk on Feb 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and "Read and internalize the full PRD content (with all comments)" from a GitHub issue via
gh issue view <number>, which is user-generated public content the agent will interpret and act on (creating new issues), enabling indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches the PRD at runtime via a GitHub issue URL (e.g. https://github.com///issues/ using
gh issue view) and uses that fetched content to directly drive the agent's prompts/instructions for drafting issues, so the external issue URL is a required runtime dependency that controls the agent.
Audit Metadata