xperiencify

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to use Membrane to proxy requests to the Xperiencify API (see "Proxy requests" and the "membrane request CONNECTION_ID /path/to/endpoint" examples) and the documented resource list includes user-generated content types like "Forum Post", "Blog Post", and "Comment", so the agent can fetch and act on untrusted third-party content from Xperiencify.