longbridge-portfolio

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to configure a Model Context Protocol (MCP) server using the vendor's official endpoint: https://openapi.longbridge.com/mcp. This is an expected integration for a skill authored by Longbridge.
  • [DATA_EXFILTRATION]: The skill is designed to retrieve and display sensitive financial information, including account balances, net asset value, and detailed profit/loss data. However, it contains explicit privacy constraints, forbidding the agent from echoing this data into shared environments like pull request descriptions or tickets, and requiring user confirmation before displaying exact figures if third-party observation is suspected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 02:19 PM