d2l-brightspace

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md instructs the agent to connect to D2L Brightspace via the Membrane CLI and run actions that can fetch user-generated content (e.g., "Discussion Forum -> Post", Announcements, Content) from the LMS (see the entities list and the action list/run examples), so untrusted third-party posts could be read and influence subsequent agent actions.