teamcamp

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to connect to Teamcamp via the Membrane CLI (e.g., "membrane connect --connectorKey teamcamp") and to list and run actions that return Teamcamp data (tasks, attachments, action outputs), meaning the agent will fetch and read user-generated/untrusted Teamcamp content as part of its workflow.