github-review-iteration

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly fetches and ingests public PR content (untrusted, user-generated) from GitHub as part of its required workflow—see the required invocation of "../review-fetch-phase/scripts/fetch-review-state.mjs --pr <PR_URL>" in SKILL.md and review-orchestrator.md (and scripts/review-iterate.mjs), and that fetched review-state.json is read and triaged to drive implementation decisions, so third-party content can influence tool actions.