china-expert

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of informational markdown files providing background knowledge and perspectives. It contains no executable scripts, binary files, or automated network requests.
  • [PROMPT_INJECTION]: The instructions set a specific persona and viewpoint but do not attempt to bypass core safety guardrails, extract system prompts, or override the agent's underlying instructions.
  • [DATA_EXFILTRATION]: No commands or patterns were found that attempt to access sensitive files (such as credentials or SSH keys) or transmit data to external servers.
  • [REMOTE_CODE_EXECUTION]: There are no instances of external package installation or remote script execution (e.g., curl | bash). All content is static text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:38 PM
Security Audit — agent-trust-hub — china-expert