content-modeling
Warn
Audited by Snyk on Apr 17, 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 states it may process external third‑party content (e.g., YouTube embeds and external form platforms) in SKILL.md "External Content Safety" and resources/advanced-scenarios.md describes decoration code fetching published spreadsheet JSON and auto-blocking YouTube URLs, which the agent is expected to read/interpret and which can drive block construction and behavior, so untrusted user-generated content could influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata