skills/acaprino/daodan/ibkr/Gen Agent Trust Hub

ibkr

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script ibkr_gateway.py downloads the IB Gateway standalone installer from Interactive Brokers' official servers (download2.interactivebrokers.com). It also fetches the IBC automation tool from its official GitHub repository. These downloads are required to provision the local trading infrastructure described in the skill instructions.
  • [COMMAND_EXECUTION]: The skill utilizes subprocess.run to execute the downloaded IB Gateway installer and subprocess.Popen to launch the gateway through IBC scripts. This execution is used to set up the headless trading environment on the user's host.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates a local config.ini file at runtime to store Gateway and IBC settings. This file incorporates credentials provided by the user via environment variables and ensures appropriate file permissions (chmod 600) are attempted for security.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Interactive Brokers venue, creating a potential surface for indirect injection.
  • Ingestion points: Market data, contract specifications (ContractDetails), and TWS error messages ingested via the ib_async library (e.g., in ibkr_probe.py).
  • Boundary markers: The skill instructions emphasize reading documentation quotes and using structured JSON output for probes to maintain data integrity.
  • Capability inventory: The skill possesses file-writing capabilities (config and PID files), network access to local API ports, and subprocess management for the Gateway/IBC lifecycle.
  • Sanitization: The scripts primarily handle structured tokens and numeric data; while no explicit string escaping is performed on venue-provided messages, the skill provides a reference TSV to grade and classify these messages before they reach the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:48 PM