prd-workflow
Warn
Audited by Snyk on Feb 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's automated data-gathering workflow fetches external Confluence and Figma pages at runtime (e.g., https://company.atlassian.net/wiki/spaces/PLAN/pages/12345678 and https://www.figma.com/design/example/ID?node-id=1-1) and injects that fetched content into the PRD-generation prompt, so remote content directly controls the agent's instructions.
Audit Metadata