ai-model-wechat
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the processing of untrusted user data through AI model interfaces, creating a surface for indirect prompt injection. \n
- Ingestion points: The
messagesparameter in thegenerateTextandstreamTextfunction calls withinSKILL.md. \n - Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the provided code snippets. \n
- Capability inventory: The skill enables calling AI models to generate and stream text responses. \n
- Sanitization: There is no evidence of input validation or sanitization of user content before it is passed to the model.
Audit Metadata