devrev

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

• Third-party content exposure detected (high risk: 0.70). The skill connects to DevRev via the Membrane CLI and explicitly runs actions such as "list-conversations" and "get-conversation" (see SKILL.md "Popular actions"), meaning the agent will ingest user-generated third-party content (DevRev conversations/issues) that it must read and which could contain instructions influencing subsequent actions.