resolve-gh-issue

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 / analyze-issue step explicitly reads a GitHub issue (title/body/labels) via the gh CLI, ingesting user-generated third-party content from the issue page which is then used to generate PRDs and drive implementation and tooling decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill accepts and at runtime fetches GitHub issue content (e.g., https://github.com/org/repo/issues/42 via gh issue view), and that external issue body/title is directly used to generate prompts/instructions (PRD, task plan, and implementation), so the external URL content can control agent behavior.