china-social-research

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard research workflow using vendor-provided capabilities (sandbase_describe_tool, sandbase_call_tool) for accessing public social media data.
  • [SAFE]: Instructions strictly limit the agent to read-only operations and emphasize factual reporting and source attribution.
  • [SAFE]: No dangerous capabilities, such as arbitrary command execution, file system writes, or network exfiltration to unauthorized domains, were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 07:39 AM
Security Audit — agent-trust-hub — china-social-research