aliyun-adb-mysql
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill references standard Alibaba Cloud credential locations to facilitate resource management.
- The instructions in
SKILL.mdpoint to the use of environment variables likeALIBABACLOUD_ACCESS_KEY_SECRETand the shared configuration file at~/.alibabacloud/credentials. - These are the industry-standard locations for the vendor's CLI and SDK credentials. The skill does not contain any code or instructions to transmit these credentials to unauthorized external destinations.
- [EXTERNAL_DOWNLOADS]: The skill includes a utility to fetch service metadata from a well-known service provider.
- The script
scripts/list_openapi_meta_apis.pyfetchesapi-docs.jsonfromapi.aliyun.com. - This activity is limited to fetching official documentation from the cloud provider's public metadata endpoints to inventory available API operations.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through the ingestion of external metadata.
- Ingestion points: The
scripts/list_openapi_meta_apis.pyscript downloads and parses JSON metadata from Alibaba Cloud's API documentation service. - Boundary markers: The script does not use specific delimiters or instructions to prevent the agent from following directives embedded in the metadata.
- Capability inventory: The skill has the capability to perform resource lifecycle and configuration operations on AnalyticDB for MySQL using the Alibaba Cloud SDK.
- Sanitization: The script performs basic structural validation by specifically extracting API names from the JSON payload, though it does not sanitize the text content of those strings.
Audit Metadata