prd-to-issues

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 a PRD from GitHub using "gh issue view (with comments)" which ingests untrusted, user-generated content (GitHub issue body and comments) that the agent must read and use to decide how to break the PRD into issues.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs fetching a PRD at runtime from a GitHub issue URL (e.g., https://github.com///issues/ via gh issue view), and that fetched issue content is injected into the agent's context to drive how it breaks down the PRD, so the external URL directly controls the agent's prompts.