disqo

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 use Membrane to run actions and proxy requests against the Disqo API (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") to retrieve Disqo data such as Responses (survey answers), which are untrusted, user-generated third-party content the agent would read and that could influence subsequent actions.