longbridge-market-data
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact extensively with the local environment using the
longbridgeCLI tool. It utilizes various subcommands (e.g.,quote,depth,kline,ipo) to retrieve market data and manage trading activities. - [EXTERNAL_DOWNLOADS]: The documentation provides instructions for installing the vendor's official CLI tool using Homebrew (
brew tap longbridge/tap && brew install longbridge/tap/longbridge-terminal). These resources are hosted on the vendor's official infrastructure and represent standard deployment practices. - [PROMPT_INJECTION]: The skill exhibits a surface for Indirect Prompt Injection (Category 8):
- Ingestion points: The agent processes real-time and historical market data (quotes, IPO details, etc.) retrieved from the Longbridge platform.
- Boundary markers: No explicit instructions or delimiters are provided to the agent to treat the retrieved market data as untrusted content.
- Capability inventory: The skill includes high-impact capabilities such as placing IPO orders (
ipo orders) and managing authentication sessions (longbridge auth login). - Sanitization: There is no evidence of sanitization or validation of the market data before it is incorporated into the agent's context.
Audit Metadata