longbridge-capital-flow

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the local binary longbridge to retrieve market data.
  • Evidence: Found in scripts/cli.py within the call_longbridge function.
  • Safety Measures: The script uses subprocess.run with a list of arguments (not a shell string), effectively preventing command injection. Additionally, the stock symbol input is strictly validated against a regex pattern (^[A-Z0-9]+\.(US|HK|SH|SZ|SG)$) before execution.
  • [SAFE]: Analysis of the skill's code and instructions found no malicious patterns.
  • No hardcoded credentials or sensitive data exposure were detected.
  • No obfuscation techniques or persistence mechanisms are present.
  • External references point to official repositories associated with the vendor's financial services.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 05:47 PM