aliyun-airec-manage
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill instructions direct the agent to check the shared configuration file at
~/.alibabacloud/credentialsfor authentication. While this is standard practice for Alibaba Cloud tooling, it involves access to a sensitive file path that contains cloud provider secrets. - [EXTERNAL_DOWNLOADS]: The script
scripts/list_openapi_meta_apis.pydownloads resource metadata and API documentation from Alibaba Cloud's official metadata service (api.aliyun.com). - [INDIRECT_PROMPT_INJECTION]: The skill ingests external JSON data from remote API documentation to list available operations, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: The script
scripts/list_openapi_meta_apis.pyfetches JSON fromapi.aliyun.comviaurllib.request. - Boundary markers: No explicit delimiters or boundary markers are used to separate the ingested metadata from the agent's internal instruction context.
- Capability inventory: The skill has the ability to execute local Python scripts, perform network requests, and write output files to the local directory.
- Sanitization: The skill does not perform sanitization or validation on the ingested JSON content beyond basic parsing.
- [DYNAMIC_EXECUTION]: The skill performs compilation checks on its own scripts using
python3 -m py_compileand executes a local Python script for API discovery.
Audit Metadata