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 user-generated reviews from Judge.me (e.g., "List Reviews", "Get Review" actions) via Membrane action runs described in SKILL.md, and those third-party review texts are read and used to drive actions like creating replies or updating review status, which could allow indirect prompt injection from untrusted public content.