ibkr-api-skill

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the ib_async Python library and references multiple community-developed GitHub repositories for MCP servers (e.g., ArjunDivecha/ibkr-mcp-server, code-rabi/interactive-brokers-mcp). These are external dependencies hosted on individual developer accounts.
  • [COMMAND_EXECUTION]: Provides detailed Python implementations and MCP tools for executing sensitive financial operations, including order placement, cancellation, and multi-account portfolio management through the IBKR TWS and Client Portal APIs.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its integration with external financial data.
  • Ingestion points: Retrieves market data, account summaries, and positions from the IBKR API as described in SKILL.md and connection-patterns.md.
  • Boundary markers: There are no defined delimiters or specific instructions provided to ignore or sanitize embedded commands within the data returned by the brokerage service.
  • Capability inventory: The skill includes powerful execution tools such as place_order and reqGlobalCancel across various account types.
  • Sanitization: No logic is present to sanitize or validate strings returned from the API before they are used to inform the agent's actions or reasoning.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 07:12 PM