alicloud-ai-research-qwen-deep-research
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
dashscopepackage, which is the official Python SDK for Alibaba Cloud Model Studio. This is a standard dependency for accessing the required research models. - [COMMAND_EXECUTION]: Local shell commands are used for environment validation (creating directories and checking Python script compilation) and for running a local preparation script. These operations are transparent and limited to the skill's own directory structure.
- [DATA_EXFILTRATION]: The skill manages interactions with Alibaba Cloud APIs. It correctly advises the use of environment variables or standard local configuration files for API keys, avoiding hardcoded credentials or unsafe transmission methods.
- [PROMPT_INJECTION]: The skill ingests user-defined research topics to build API payloads. This is the intended primary functionality of the research skill and does not include any instructions designed to bypass safety filters or override agent behavior.
Audit Metadata