frameio

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

• Third-party content exposure detected (high risk: 0.80). This skill uses Membrane to fetch and act on Frame.io content (see SKILL.md "Popular actions" like List Comments / Get Asset and "Running actions"), meaning the agent will read and interpret user-generated third-party assets/comments/review links from Frame.io—which could contain untrusted instructions that influence subsequent actions.