gh-pr-review-responder

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

• Third-party content exposure detected (high risk: 0.90). This skill's workflow and scripts (scripts/fetch_review_threads.py using gh api GraphQL and SKILL.md) fetch and present reviewer comment bodies from GitHub (user-generated/untrusted content) which the agent is explicitly instructed to read and use to decide KEEP vs DISCARD, implement changes, and post replies, so third-party content can materially influence actions.