alibabacloud-pai-eas-service-deploy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to copy the DescribeServiceEndpoints output (which includes an AccessToken) into the final response and to include curl examples that embed the AccessToken verbatim, requiring the LLM to output a secret value.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content contains explicit instructions to retrieve and include service AccessToken (and other sensitive endpoint/auth fields) in final outputs, which enables credential exposure/data exfiltration and represents a high-risk deliberate behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's pre-checks include the runtime command curl -fsSL https://aliyuncli.alicdn.com/install.sh | bash, which fetches and executes remote code as a mandatory installation step (https://aliyuncli.alicdn.com/install.sh), so it directly executes external code during runtime.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs installing/upgrading the Aliyun CLI via a remote curl|bash installer, installing/updating CLI plugins, and running many direct shell commands (execute_shell_command), which modify the host system state and can require elevated/system-level changes.