pr-review-comment-response

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly queries GitHub pull request review threads (see "Phase 1: Inventory" and the included GraphQL query) and ingests reviewer comment bodies—untrusted, user-generated content that the agent must read and act on to decide dispositions and post replies, creating a clear vector for indirect prompt injection.