marketing-video
Warn
Audited by Snyk on Apr 27, 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's workflow explicitly includes a "Live Website URL Audit" (references/shared-patterns.md § Starting Context Router and SKILL.md Pre-Flight/Context C) and instructs use of an agent-browser/WebFetch to audit public URLs, so the agent will fetch and interpret arbitrary public web pages provided at runtime, which are untrusted third-party content that can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata