The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the official aliyun (Alibaba Cloud CLI) tool via a Python script to fetch cloud resource data. The execution is handled safely using subprocess.run with an argument list, which prevents command injection vulnerabilities.
[COMMAND_EXECUTION]: The script includes built-in security validation for user-provided parameters, such as a whitelist for regions and range checking for the concurrency worker count.
[DATA_EXPOSURE]: The skill generates temporary JSON files in /tmp to store query results during processing. These files are automatically deleted after the report is generated, minimizing the risk of data residue.
[PROMPT_INJECTION]: The instructions in SKILL.md include strong formatting requirements to ensure output completeness and prevent the AI from summarizing data. While forceful, these instructions are aimed at usability and do not attempt to bypass safety filters or override agent constraints.
[CREDENTIALS_SAFE]: No hardcoded API keys or secrets were found. The skill relies on the user's existing Alibaba Cloud CLI configuration, and the documentation correctly guides users to apply the principle of least privilege using RAM policies.

alibabacloud-dts-task-query