The Agent Skills Directory

[COMMAND_EXECUTION]: The skill automates interactions with Alibaba Cloud services by executing the aliyun command-line interface.
Evidence: scripts/accounts.py, scripts/baseline.py, and scripts/vuln.py utilize subprocess.run and asyncio.create_subprocess_exec to invoke CLI commands for identity verification, account listing, and triggering report exports. Commands are constructed as lists to prevent shell injection.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download of official vendor tools and security report archives.
Evidence: SKILL.md directs users to the official Alibaba Cloud GitHub repository for CLI installation. The Python scripts baseline.py and vuln.py programmatically download report files from links provided by the Alibaba Cloud SAS API using urllib.request. These represent trusted vendor resources.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data in the form of security vulnerability and baseline reports from cloud APIs.
Evidence: Reports are fetched in scripts/baseline.py and scripts/vuln.py and subsequently merged into Excel files using openpyxl. While this data originates from an external source, it is processed as structured content for reporting rather than being interpreted as instructions for the agent.
[SAFE]: The skill implements secure patterns for credential management and environment isolation.
Evidence: The skill explicitly instructs users to use aliyun configure for secrets management instead of hardcoding credentials. It also encourages the use of Python virtual environments to isolate dependencies.

alibabacloud-sas-multiaccount-manage