address-pr-comments

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

• Third-party content exposure detected (high risk: 0.80). This skill directly fetches and normalizes user-generated PR comments from GitHub (see scripts/list_comments.py which uses gh pr view and gh api repos/<owner>/<repo>/pulls/<pr>/comments and extracts "Prompt for AI Agents" blocks), so the agent will read and interpret untrusted third-party content from GitHub comments.