The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill instructions specify the use of sensitive environment variables including ALIBABACLOUD_ACCESS_KEY_ID and ALIBABACLOUD_ACCESS_KEY_SECRET. It also directs the agent to read credentials from the local shared configuration file at ~/.alibabacloud/credentials.
[EXTERNAL_DOWNLOADS]: The script scripts/list_openapi_meta_apis.py fetches product metadata and API definitions from Alibaba Cloud's official metadata service at api.aliyun.com.
[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands, including running local Python scripts for API discovery and using py_compile for script validation.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints, which could potentially contain malicious instructions if the source were compromised.
Ingestion points: Data is fetched from https://api.aliyun.com/meta/v1/products/ via the list_openapi_meta_apis.py script.
Boundary markers: The skill does not implement specific delimiters or warnings to isolate the fetched external data from the agent's core instructions.
Capability inventory: The agent is authorized to execute Python scripts, write files to the output directory, and perform cloud resource management actions.
Sanitization: The script performs standard JSON parsing but does not include explicit validation or sanitization of the remote content before writing it to markdown files used by the agent.

aliyun-aimiaobi-generate