running-in-ci

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and read PR/issue titles, bodies, comments, diffs, and workflow artifacts from GitHub (e.g., via gh pr view, gh pr diff, gh issue view, and gh run download), which are user-generated/untrusted third‑party content and are used to drive decisions and next actions.