longbridge-derivatives
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is primarily designed to facilitate the execution of the
longbridgeCLI tool on the host system to fetch financial data. Commands such aslongbridge option quote,longbridge warrant list, andlongbridge klineare used throughout the reference files. - [INDIRECT_PROMPT_INJECTION]: The skill provides templates for the agent to execute shell commands using inputs provided by the user.
- Ingestion points: The agent accepts user input for symbols (
<SYMBOL>), option codes (<OCC_SYMBOL>), and dates (<YYYY-MM-DD>) which are then interpolated into CLI commands. - Capability inventory: The skill utilizes shell command execution via the
longbridgeCLI to perform data retrieval and analysis tasks across all included reference files. - Boundary markers: There are no explicit instructions or delimiters defined to sanitize or validate user-provided strings before they are passed to the shell.
- Sanitization: The instructions do not specify any validation logic for ticker symbols or other parameters, relying on the underlying platform's execution safety.
Audit Metadata