truora

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md instructs the agent to run Membrane actions against the Truora connector (e.g., via "membrane action run" and connection setup) and explicitly lists data types such as "News Article, Social Media Profile, Online Review, Blog Post, Forum Post" indicating the agent will fetch and read untrusted, user-generated third-party content from public sources as part of its workflow.