longbridge-anomaly

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes local CLI tools (longbridge) and MCP tools (mcp__longbridge__*) to retrieve market data. These are documented vendor resources from 'longbridge'.
  • [SAFE]: The functionality is restricted to read-only operations, specifically scanning for unusual price/volume movements and displaying intraday trade statistics.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized command execution was found within the skill content.
  • [SAFE]: The skill includes robust error handling and instructions for the agent to resolve symbol mappings and handle environment errors gracefully.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 05:47 PM