lead-qualification
Warn
Audited by Snyk on May 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Steps 2–3 explicitly instruct the agent to WebSearch public sources (e.g., LinkedIn profiles, company domains) and WebFetch company websites, requiring it to read and act on untrusted third-party web content to determine ICP fit and next actions, which could enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata