material-usage-loss-check-free

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (critical risk: 1.00). The skill contains instructions steering the user to execute an external script to purchase a paid version via cryptocurrency/token/payment infrastructure.

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 npx -y @alipay/agent-payment@latest install, which dynamically downloads and runs arbitrary remote code from an npm package without pinning an immutable identifier or digest, constituting a weak runtime external dependency.