Cold Email
Warn
Audited by Snyk on Apr 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to "Search target professor info (WebSearch + webReader for homepage, Google Scholar)" in the Email Generation Process, meaning it fetches and reads open/public third-party webpages (professor homepages, Google Scholar) and uses that untrusted content to determine specific research connections that will drive email content and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata