NYC

ai-model-web

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill demonstrates processing user-supplied data through the messages array which is then sent to an external AI model.
  • Ingestion points: messages parameter in generateText() and streamText() methods.
  • Boundary markers: Not present in the provided code snippets.
  • Capability inventory: Network operations (API calls to CloudBase services).
  • Sanitization: Not present; developers are expected to implement their own validation.
  • [External Downloads] (SAFE): The skill recommends installing @cloudbase/js-sdk via npm. This is the official SDK for Tencent CloudBase and is considered a trustworthy source.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:00 PM