chain-store-settlement-check-free

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill contains instructions directing the AI assistant to execute a command to install an external payment agent and purchase a paid product through an external link.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute a command (npx -y @alipay/agent-payment@latest install) that fetches and runs a package from an arbitrary remote source (@alipay/agent-payment), creating an unverified runtime external dependency with weak/unknown provenance.