alicloud-ai-research-qwen-deep-research-test

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a command-line example that executes a local Python script (prepare_deep_research_request.py) located within the repository structure. This is standard behavior for a smoke test and does not involve unauthorized privilege escalation or suspicious shell operations.
  • [PROMPT_INJECTION]: No evidence of prompt injection, instruction overrides, or safety filter bypass attempts was found in the skill's documentation or commands.
  • [DATA_EXFILTRATION]: The skill does not access sensitive files (e.g., credentials, SSH keys) or perform network operations to untrusted domains. It writes output to a local directory (output/).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 01:20 AM