judgeme

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes user-generated reviews and related data from the third-party Judge.me service (see "Popular actions" like List Reviews / Get Review and the "Proxy requests" /path/to/endpoint in SKILL.md), so untrusted public content would be read and could influence follow-up actions such as creating replies or updating review status.