aliyun-sas-manage
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches API metadata from Alibaba Cloud's official OpenAPI endpoint (
api.aliyun.com). This is a legitimate operation to discover available service capabilities for Security Center. - [COMMAND_EXECUTION]: Provides a local Python script (
scripts/list_openapi_meta_apis.py) to process API documentation and generate local inventory files used for resource management. - [INDIRECT_PROMPT_INJECTION]: The skill ingests JSON-formatted metadata from an external source. While this creates a theoretical surface for malicious content to influence agent behavior, the source is an official, well-known service endpoint.
- Ingestion points:
scripts/list_openapi_meta_apis.pyfetches data fromapi.aliyun.com. - Boundary markers: None explicitly implemented for the processed external JSON content.
- Capability inventory: Filesystem writes to the
output/directory and performance of Alibaba Cloud API operations (create/update/delete). - Sanitization: The script extracts specific identifier fields from the payload but does not apply text sanitization to descriptions or documentation fields before they are presented to the agent.
Audit Metadata