freedcamp

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

• Third-party content exposure detected (high risk: 0.90). This skill retrieves user-generated Freedcamp content (e.g., issue details and comments via the documented actions like "get-issue" / "list-issues" and the Membrane proxy membrane request) as part of its workflow, so untrusted third-party text could be read and influence subsequent agent actions.