checkmarket

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md "Proxy requests" section explicitly shows using membrane request CONNECTION_ID /path/to/endpoint to fetch data from the CheckMarket API (e.g., survey/respondent data), which is third-party user-generated content the agent would read and could materially influence subsequent actions.