aliyun-cli-skills
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads Aliyun CLI installation packages and scripts from the official Alibaba Cloud CDN (
aliyuncli.alicdn.com). This is standard behavior for tool setup and utilizes a well-known service domain. - [REMOTE_CODE_EXECUTION]: Installation instructions for Linux and macOS involve fetching a shell script via
curland executing it directly withbash. While this pattern is typically high-risk, it is used here to install official tooling from a trusted vendor. - [COMMAND_EXECUTION]: The skill is designed to construct and execute
aliyunCLI commands on the host system. It correctly identifies the need for elevated privileges (sudo) when moving binaries to system paths like/usr/local/bin/. - [PROMPT_INJECTION]: As the skill translates user natural language into executable shell commands, there is an inherent risk of indirect prompt injection. However, the skill mitigates this by instructing the agent to use
--dryrunfor verification and to seek explicit user confirmation before performing any destructive or modification-based operations.
Audit Metadata