iterate-pr

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required workflow uses fetch_pr_feedback.py and fetch_pr_checks.py to retrieve PR review feedback and CI log_snippet from GitHub for the PR’s authored content, which is outsider-authored free text (e.g., issue/review comments/logs) that the LLM processes at runtime before selecting specific items.