pr-retro

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md Phase 3 "Feedback Extraction" explicitly instructs fetching reviewer bodies and comments from GitHub (e.g., gh pr view --json reviews and gh api repos///pulls//comments), which ingests untrusted, user-generated third-party content that the agent is expected to read and use to derive lessons and next actions.