ai-model-wechat

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Tencent Cloud and WeChat developer APIs for cloud-based AI functions. It does not require external packages or execute unauthorized remote code.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection.\n
  • Ingestion points: The messages array in generateText() and streamText() methods (SKILL.md) accepts external content.\n
  • Boundary markers: Not present in example code snippets.\n
  • Capability inventory: Orchestrates network communication with LLMs (Hunyuan, DeepSeek) via WeChat infrastructure.\n
  • Sanitization: Not demonstrated in provided code; implementers are responsible for validating untrusted input.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 03:49 AM