miniprogram-development
Fail
Audited by Snyk on Nov 17, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate WeChat Mini Program development guide, but its setup prompt tells the agent to fetch and follow instructions from a remote URL, an unvetted channel, which is risky toward the user without showing malicious intent.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The message-push workflow consumes text that WeChat end users send to the mini program's customer-service channel (MsgType
text), and the required verification step has the agent or user review those receiver-function logs in the IDE, so outsider text reaches the agent without any item being selected first.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata