feathery

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and read third-party Feathery data (e.g., "List Form Submissions", "Get User Data", and the "membrane request CONNECTION_ID /path/to/endpoint" proxy to the Feathery API), which can return untrusted user-generated submissions that the agent is expected to interpret and that could materially influence subsequent actions.