call-prep
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). High: the skill’s REQUIRED runtime flow includes “ALWAYS run web search” (public web content like “[Company] news/funding/leadership” and attendee LinkedIn profiles) which is fetched at runtime and ingested as readable text into the LLM context, enabling outsider-authored free text via arbitrary web pages.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata