longbridge-buffett-moat-stock-screener

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses established vendor tools (longbridge CLI and MCP) for its primary data fetching. All commands are limited to financial data retrieval (quotes, fundamentals, and reports).
  • [SAFE]: Data transparency is emphasized through a mandatory 'Data Source Appendix' that tracks every figure and source (including WebSearch hits with URLs and dates).
  • [SAFE]: The skill employs specific disqualification criteria and reconciliation gates to ensure data integrity and prevent the analysis of high-risk or inappropriate asset classes (e.g., ST stocks, pre-revenue biotech).
  • [SAFE]: Indirect prompt injection risks are mitigated as the external data (from WebSearch) is used for specific qualitative scoring dimensions and is clearly delimited in the output. The skill lacks dangerous capabilities such as arbitrary file writing or code execution.
  • [SAFE]: No obfuscation, credential exposure, or unauthorized network operations were detected. All external references are context-appropriate for a financial screener.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 11:53 AM