aliyun-adb-mysql
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches OpenAPI metadata from the official Alibaba Cloud domain
api.aliyun.comto dynamically discover supported API operations and schemas. This is a well-known service used for its intended purpose. - [COMMAND_EXECUTION]: The skill executes local Python scripts (
scripts/list_openapi_meta_apis.py) and utilizespy_compileto validate script integrity within the skill directory. - [CREDENTIALS_UNSAFE]: The skill facilitates cloud resource management by accessing Alibaba Cloud credentials via standard environment variables and the shared configuration file
~/.alibabacloud/credentials. These operations are consistent with the skill's primary purpose. - [PROMPT_INJECTION]: The skill ingests data from a remote API metadata endpoint to inform the agent's workflow. While this creates a potential surface for indirect prompt injection, the reliance on official vendor endpoints minimizes risk. Evidence Chain: 1) Ingestion point:
api.aliyun.comvialist_openapi_meta_apis.py; 2) Boundary markers: Not explicitly defined for external metadata; 3) Capability inventory: Local script execution and cloud API calls; 4) Sanitization: None implemented for the metadata payload.
Audit Metadata