ai-model-wechat
Warn
Audited by Snyk on May 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's "Custom Onboarding" flow explicitly allows registering arbitrary third‑party/self‑hosted OpenAI‑compatible endpoints via CreateAIModel (BaseUrl) and then the Mini Program calls generateText/streamText which return and consume raw model responses (see "Custom Onboarding" and the "generateText()/streamText()" sections), so untrusted external model outputs can be ingested and influence behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata