NYC

ai-model-wechat

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The content consists of API documentation and implementation details for WeChat Mini Programs. It does not contain instructions to override AI safety protocols, ignore previous rules, or reveal system prompts.
  • Data Exposure & Exfiltration (SAFE): No sensitive data access or hardcoded credentials were found. The use of '<YOUR_ENV_ID>' is a standard placeholder for configuration.
  • Remote Code Execution (SAFE): The skill does not perform any external downloads, package installations, or piped shell executions. It relies on the built-in WeChat base library (3.7.1+).
  • Obfuscation (SAFE): The markdown and JavaScript code are clear and human-readable with no hidden characters, Base64 encoding, or homoglyph attacks.
  • Indirect Prompt Injection (LOW): The skill processes user-supplied messages through AI model calls. While the documentation doesn't explicitly show sanitization, the restricted environment of a WeChat Mini Program and the lack of sensitive system capabilities (like file system or shell access) in the provided examples minimize the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:49 PM