cloudflare-queues
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (LOW): The skill contains templates demonstrating how to use
fetchto send data to third-party services (e.g., Stripe, Resend, Slack) and how to call external URLs specified within message payloads. These are standard functional behaviors for the intended use cases of email, payment processing, and webhook handling. - [Indirect Prompt Injection] (LOW): The skill defines consumer templates that ingest and process untrusted data from message queue bodies, which can trigger network or database actions.
- Ingestion points: The
message.bodyparameter within thequeuehandler in all consumer templates (e.g.,queues-consumer-basic.ts). - Boundary markers: No specific boundary markers or 'ignore' instructions are used for data processed from the queue.
- Capability inventory: Capabilities include external network requests (
fetch), Cloudflare D1 database operations (env.DB), and Cloudflare KV storage operations (env.LOGS). - Sanitization: No explicit sanitization or validation logic is included in the templates, as they are intended for developer customization.
Audit Metadata