schoology

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and operate on Schoology data via Membrane commands (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") and lists user-generated resources like Discussions, Pages, and Blogs, so the agent would read untrusted third-party content from Schoology that could contain instructions influencing actions.