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 tells the agent to fetch the PRD from a GitHub issue ("fetch it with gh issue view <number> (with comments)") — a user-generated, third-party source the agent must read and act on to create issues, which could carry instructions that influence its behavior.

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 the PRD at runtime using the GitHub CLI (gh issue view ), i.e. remotely loading content from URLs like https://github.com///issues/, and that fetched content is injected into the agent context and directly controls the prompts/instructions.