content-modeling
Warn
Audited by Snyk on May 15, 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.md and resources (notably the "External Content Safety" section, the Forms section in resources/advanced-scenarios.md, and Auto-Blocked/YouTube embed examples) explicitly describe fetching and processing third‑party content such as YouTube URLs, external form services, and published spreadsheet JSON, which the agent is expected to read/interpret as part of its content‑modeling workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata