ib-account
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions provide specific shell commands to execute the
scripts/account.pyfile usinguv run pythonorpython. This is the intended mechanism for the agent to retrieve account data. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves account summaries from an external source (Interactive Brokers API) which are then processed by the agent.
- Ingestion points: Account data returned as JSON by the
scripts/account.pyscript (e.g., net liquidation, cash, buying power). - Boundary markers: The output is explicitly structured as JSON, which helps the agent distinguish between data and instructions.
- Capability inventory: The skill allows local script execution and reading of environment variables for configuration.
- Sanitization: The script outputs structured JSON with specific fields (
accounts,connected), limiting the surface area for unexpected text processing.
Audit Metadata