Professor Match

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly uses WebSearch and the webReader to fetch and read professors' public faculty homepages and Google Scholar/DBLP profiles (Step 2 and Step 3), i.e., untrusted public web content that the agent must interpret to make matching decisions, which could allow indirect prompt injection.