campaign-copywriting
Warn
Audited by Snyk on Apr 30, 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 explicitly instructs the agent to research and ingest public website content and social/professional signals (e.g., "Website URL
- Research homepage, features, pricing, case studies, about page", LinkedIn/review examples and AI-generated variables) and uses that untrusted third-party content to populate variables and drive campaign decisions and uploads, so external pages could inject instructions that affect behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata