junip

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly exposes Junip user-generated review content via Membrane actions such as "list-reviews" and "get-review" (Junip API) which the agent is expected to fetch and interpret as part of its workflow, creating a vector for untrusted third‑party content to influence decisions.