github-code-review

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

• Third-party content exposure detected (high risk: 0.85). For PR interactions, the skill fetches outsider-authored PR body text and metadata from GitHub’s API (e.g., pr['body'] via curl .../pulls/$PR_NUMBER), which is then printed/ingested into the agent’s LLM context; this is free-form text authored by the PR author/others.