aliyun-opensearch-search
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external search results, representing a vulnerability surface where untrusted content could influence agent behavior.
- Ingestion points: The
ha3.search()method inSKILL.mdandscripts/quickstart.pyretrieves documents from a user-defined OpenSearch endpoint. - Boundary markers: The provided scripts do not implement specific boundary markers or delimiters for the search results returned to the agent.
- Capability inventory: The skill performs network operations via the Alibaba Cloud SDK to communicate with the OpenSearch API and writes search results to the
output/directory. - Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved search content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
alibabacloud-ha3enginepackage from the official Python package registry (PyPI). This is a well-known service provided by a major cloud provider.
Audit Metadata