building-ai-agent-on-cloudflare
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 agent clearly ingests untrusted user-generated content from client connections (e.g., onMessage/handleChat and ChatBot.onChatMessage where incoming WebSocket messages and userMessage are parsed and passed into env.AI.run), exposing it to indirect prompt injection.
Audit Metadata