virtuals
Warn
Audited by Snyk on Feb 20, 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 calls createVirtualsFeed and uses its Runtime API (e.g., handleAgent in index.ts calling f.getAgent and printing agent.description, agent.personality, and socials) to fetch and display user-created/public agent content from the Virtuals marketplace (virtuals.io), which is untrusted third‑party content that the agent will read and could contain embedded instructions.
Audit Metadata