content-modeling
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly describes ingesting and auto-processing public third-party content—e.g., the Auto-Blocked YouTube embed example that parses/presents a https://www.youtube.com/... URL and the Forms/Configuration sections that reference embedding/fetching external services (Marketo/HubSpot/Google Forms) and blog APIs—meaning the agent is expected to read/interpret untrusted public URLs/content.
Audit Metadata