longbridge-ark-analysis

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates financial analysis using the vendor's own command-line interface tool (longbridge) and a fallback MCP server. All shell commands are scoped to stock market data retrieval (financial-reports, quotes, news, and filings), which is consistent with the skill's stated purpose.- [SAFE]: External data gathering is performed through authorized web searches targeting reputable financial and technology research organizations (e.g., Gartner, IDC, BloombergNEF, IRENA). These are well-known services and do not constitute a security risk.- [SAFE]: The skill implements a 'Reconciliation Gate' (勾稽校验), a security and integrity feature that verifies the consistency of financial data across different statements (Income Statement vs. Balance Sheet vs. Cash Flow) before proceeding with analysis. This helps prevent errors or manipulation of the data-driven output.- [SAFE]: The prompt logic is well-structured and focuses on analytical reasoning without any attempts to bypass safety filters, extract system instructions, or hide malicious behavior. All external resources and tools used are verified vendor assets.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 11:55 AM
Security Audit — agent-trust-hub — longbridge-ark-analysis