crisp

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md instructs the agent to use Membrane to connect to Crisp and run actions like list-messages and get-conversation, which fetch user-generated conversation/messages from a third‑party platform (Crisp) that the agent will read and which could materially influence subsequent actions.