lever

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and acts on user-generated Lever data via Apideck's ATS API (see SKILL.md examples like "List applicants in Lever" and the Proxy flow with x-apideck-downstream-url that calls Lever endpoints), so untrusted third-party content could be read and influence agent actions.