gradeus

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to list and fetch Grade.us data (e.g., "List Reviews" and using membrane action run / membrane request to call Grade.us APIs), which are public/third‑party, user‑generated reviews and content that the agent is expected to read and could materially influence subsequent actions.