document360

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

• Third-party content exposure detected (high risk: 0.90). The skill uses the Membrane CLI to fetch Document360 content (e.g., "Get Article By URL", "List Articles" in SKILL.md's Popular actions), which pulls untrusted third-party/user-authored knowledge-base articles that the agent is expected to read and act on—allowing those pages to influence decisions and follow-up actions.