interview-guide-generator

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and extract publicly available information from a LinkedIn profile URL in Step 3 ("LinkedIn profile URL — fetch and extract publicly available information"), which is an untrusted, user-generated third-party source that the agent must read and use to personalize questions and decisions.