schoology

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md shows the agent connects to external Schoology instances via the Membrane CLI and runs actions that fetch and operate on user-generated Schoology content (e.g., Discussions, Blogs, Pages, Assignments, Updates) so untrusted third‑party content from Schoology could be ingested and influence agent behavior.