longbridge-market-data
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
longbridgecommand-line tool with various subcommands (such asquote,depth,kline, andcapital) to retrieve financial data. - [EXTERNAL_DOWNLOADS]: Fetches and installs the
longbridge-terminalbinary using Homebrew (brew tap longbridge/tap && brew install longbridge/tap/longbridge-terminal) from an external repository. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its data ingestion patterns.
- Ingestion points: Market data, including quotes, order books, and trade ticks, is ingested from external financial exchanges via the
longbridgeCLI. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts in the retrieved market data.
- Capability inventory: The skill has the capability to execute shell commands through the
longbridgebinary. - Sanitization: There is no evidence of explicit sanitization or validation of the data returned by the CLI before it is processed by the agent.
Audit Metadata