critic-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 3 "Context7 staleness scan" explicitly fetches external documentation (via the Context7 plugin and a fallback WebFetch to [library-website]/llms.txt) and then incorporates those fetched snippets into the review prompt and reference documentation, meaning untrusted third‑party content is read and can materially influence the agent's analysis and actions.