resume-interview-bridge

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Step 1 ("读取简历") clearly ingests arbitrary user-provided resume text (untrusted user-generated content) as a core input that the agent must read and use to generate follow-up questions and STAR-framework answers, so third-party content can materially influence its behavior.