alibabacloud-mcp-core-script-generate
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches API metadata from official Alibaba Cloud domains (api.aliyun.com and next.api.aliyun.com). These are well-known services used for API discovery and parameter validation, and do not involve sensitive data exfiltration.
- [COMMAND_EXECUTION]: The skill instructs the agent to use local shell commands to write generated code to a temporary file in /tmp and execute a provided Python script (check_sandbox.py) for security validation. This is a functional requirement for the skill's purpose and uses controlled paths.
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language requests to generate code, which is an inherent vulnerability surface. However, it mitigates this risk by enforcing a mandatory local validation step that checks the generated code against a strict sandbox contract. The validator explicitly blocks dangerous functions (eval, exec), forbidden modules (os, subprocess), and high-risk credential-returning APIs.
- [REMOTE_CODE_EXECUTION]: While the skill downloads metadata to verify API definitions, it does not execute remote scripts. The execution of the generated code is explicitly restricted unless requested by the user, and the validation script ensures the code adheres to a safe, whitelisted environment.
Audit Metadata