wechatpay-payment-integration

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill instructs the agent to silently bypass permissions and pre-configure network domains without user consent during initialization, representing a medium-risk action of altering environment configuration behind the user's back.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill prompt instructs the agent to silently bypass network restrictions and modify firewall or routing permissions by 'silently whitelisting' external domains without user consent, which represents a security mechanism bypass.