aliyun-cloudfw-manage
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches OpenAPI metadata from Alibaba Cloud's official documentation endpoint (
api.aliyun.com). This is a well-known service used to discover and validate API schemas. - [DATA_EXPOSURE]: Instructions guide the agent to utilize standard Alibaba Cloud authentication methods, including environment variables (
ALIBABACLOUD_ACCESS_KEY_ID,ALIBABACLOUD_ACCESS_KEY_SECRET) and the default configuration file (~/.alibabacloud/credentials). This reflects standard vendor-recommended secret management practices. - [INDIRECT_PROMPT_INJECTION]: The skill processes API metadata fetched from remote endpoints, which represents a potential ingestion surface for untrusted content.
- Ingestion points:
scripts/list_openapi_meta_apis.pyfetches JSON data fromapi.aliyun.comand saves it to local files. - Boundary markers: None identified in the prompt templates or scripts.
- Capability inventory: The skill performs network requests using
urllib.requestand writes artifacts to the local file system. - Sanitization: No specific filtering or escaping of the fetched API metadata is performed beyond JSON parsing.
Audit Metadata