uniify

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

• Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly instructs using Membrane to proxy requests and to list/run actions against the Uniify API (see "Proxy requests" and "Searching for actions"/"Running actions"), which will return user-generated messages/documents/channels that the agent is expected to read and act on, creating a clear vector for indirect prompt injection.