pr-review

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

• Third-party content exposure detected (high risk: 0.90). This skill's "Getting Started" instructions explicitly tell the agent to fetch and read PR data from GitHub (e.g., "gh pr view --json title,body,files", "gh pr diff " and "Read the PR description and all commits"), which ingests untrusted, user-generated third‑party content (PR descriptions/commits) that the agent is expected to interpret and that can materially influence review decisions and subsequent actions.