FAQ Builder
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: 0.90). The skill explicitly instructs mining/ingesting public, user-generated sources—e.g., "Community forum posts" and "Social media mentions" in the Customer Interaction Sources—so the agent would read untrusted third-party content as part of its workflow, enabling indirect prompt injection.
Audit Metadata