wufoo

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md instructs the agent to query and proxy requests to the Wufoo API (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint"), which will return user-generated form/entry data from a third-party service that the agent is expected to read and could materially influence subsequent actions.