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 asks for a PRD GitHub issue number/URL and instructs using gh issue view <number> to fetch the issue (and comments) from GitHub, meaning it ingests user-generated, public third‑party content that the agent will read and act on to create/triage issues.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs fetching a PRD by GitHub issue URL at runtime (e.g., https://github.com///issues/ or via gh issue view <number>), which would inject external issue content into the agent’s context and directly control its prompt/behavior.