alibabacloud-agent-toolkit-install

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill utilizes pipe-to-shell installation patterns for 'uv' and the Alibaba Cloud CLI. Specifically, it executes curl -LsSf https://astral.sh/uv/install.sh | sh and bash -c "$(curl -fsSL https://aliyuncli.alicdn.com/install.sh)". These resources originate from well-known services and the official vendor infrastructure associated with the skill author.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the agent toolkit using npx openplugin aliyun/alibabacloud-agent-toolkit, fetching packages from the official NPM registry.
  • [COMMAND_EXECUTION]: Extensive use of shell commands to manage environment state, including uv, aliyun CLI, and npx. The skill also includes a Windows PowerShell script (scripts/install-aliyun-cli-windows.ps1) that downloads the CLI binary from aliyuncli.alicdn.com and updates the user's PATH environment variable.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes output from external CLI tools.
  • Ingestion points: Commands in SKILL.md (Steps 3, 5, 6) capture CLI output from aliyun sts get-caller-identity and aliyun openapiexplorer.
  • Boundary markers: None identified.
  • Capability inventory: The skill has the capability to execute shell commands and cloud API calls across several steps.
  • Sanitization: No specific sanitization or escaping of the CLI output is implemented before the agent interprets the results.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 09:16 AM
Security Audit — agent-trust-hub — alibabacloud-agent-toolkit-install