wxa-ai-mode-dev

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The content is purely instructional and provides a technical specification for a development framework.
  • [EXTERNAL_DOWNLOADS]: The skill references official WeChat developer domains (developers.weixin.qq.com) and GitHub repositories belonging to the vendor (TencentCloudBase) and the platform owner (wechat-miniprogram). These are considered trusted sources for this development context.
  • [COMMAND_EXECUTION]: The document mentions developer-focused CLI tools (e.g., wxa-skills-validate, wxa-skills-eval) and environment settings (vConsole, service ports) which are standard for the described WeChat Mini Program development workflow.
  • [PROMPT_INJECTION]: While the skill provides instructions on how an LLM should behave (e.g., 'Do not hallucinate', '陈述事实'), these are architectural guidelines for the developer to implement within their own skill definitions and do not constitute malicious prompt injection attempts against the analyzer or the host agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 09:11 AM
Security Audit — agent-trust-hub — wxa-ai-mode-dev