aliyun-mps-manage
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches OpenAPI metadata from the official Alibaba Cloud domain (api.aliyun.com) using a Python script. This is a legitimate operation for discovering API definitions.
- [COMMAND_EXECUTION]: The skill executes a local Python script to retrieve and format API documentation for the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface for indirect prompt injection as it processes external JSON data. 1. Ingestion points: External metadata is ingested from api.aliyun.com in scripts/list_openapi_meta_apis.py. 2. Boundary markers: No explicit delimiters are used. 3. Capability inventory: The skill is designed for Alibaba Cloud media processing resource management as described in SKILL.md. 4. Sanitization: No content sanitization is performed on the ingested metadata.
- [CREDENTIALS_UNSAFE]: The skill instructions reference the standard Alibaba Cloud credential location (~/.alibabacloud/credentials) to facilitate authentication for API requests. This is standard configuration for Alibaba Cloud tools.
Audit Metadata