alibabacloud-agent-toolkit-install

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONPERSISTENCE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The installation process involves downloading and executing shell scripts directly from remote URLs using patterns like curl -LsSf https://astral.sh/uv/install.sh | sh and bash -c "$(curl -fsSL https://aliyuncli.alicdn.com/install.sh)". These targets (Astral and Alibaba Cloud) are recognized as well-known or trusted vendor services, which minimizes the security risk according to the trust policy.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the primary toolkit repository from github.com/aliyun and uses npx openplugin to retrieve additional MCP server components. These actions utilize official distribution channels appropriate for the skill's purpose.
  • [COMMAND_EXECUTION]: Multiple system-level and cloud-specific commands are invoked to verify environment readiness and manage identity tokens (e.g., aliyun sts get-caller-identity and the non-standard aliyun RamOAuth GenerateAccessToken). These are documented as necessary steps for configuring the Alibaba Cloud environment.
  • [PRIVILEGE_ESCALATION]: The Windows installation script (install-aliyun-cli-windows.ps1) is designed to be executed with -ExecutionPolicy Bypass and modifies the User-level PATH environment variable. These modifications are standard for software installers but do alter system-level execution settings.
  • [PERSISTENCE]: The skill instructs the agent to guide users in sourcing their shell profiles (such as .bashrc or .zshrc) to ensure that modifications to the PATH persist across terminal sessions, which is standard practice for CLI tool installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:10 AM