callrail

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs using the Membrane CLI to run CallRail actions (e.g., "List Calls", "List Form Submissions", "List Text Conversations" and "get-call") which fetch user-generated call transcripts, texts, and form submissions from a third-party CallRail account that the agent will read and that could materially influence subsequent actions (as shown in SKILL.md).