longbridge-peer-comparison

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is prompt-only and does not include any executable scripts or code. It defines logic for an AI agent to orchestrate existing tools.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure an external MCP server hosted at https://openapi.longbridge.com/mcp. This domain is the official platform for the vendor 'longbridge', and the reference is necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: It provides a setup command for the user to add the MCP server (claude mcp add ...). This is standard configuration documentation for MCP-based skills.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were found. The skill operates on public financial symbols and returns market data to the user.
  • [PROMPT_INJECTION]: No prompt injection, behavior overrides, or instructions to bypass safety guidelines were detected. The skill actually enforces safety by prohibiting the agent from giving investment advice.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 02:19 PM