Sales
Warn
Audited by Snyk on Feb 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). This skill explicitly accepts and ingests arbitrary public web content (e.g., "URL to product page" in Workflows/CreateNarrative.md's Step 1), so the agent would read and interpret untrusted third‑party site content as part of its workflow.
Audit Metadata