teamtailor

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using Membrane actions and proxy requests (e.g., list-job-applications, get-job-application, and membrane request) to fetch Teamtailor data (job postings, applications, candidate records) from a third-party ATS, which is user-generated/untrusted content that the agent will read and can drive follow-up actions.