gh-plan-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching live GitHub content (e.g., "gh issue view" and "gh pr view" in Core Workflow step 1 and the Source Grounding Rules) so the agent will read and base decisions on user-generated third‑party GitHub issues/PRs, which could embed instruction-like content.