Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors

Researchers propose Survivability-Aware Execution (SAE), a new security framework for AI-powered crypto trading systems that prevents execution-induced losses from compromised AI agents or malicious prompts. The system implements middleware protection between AI strategy engines and exchange executors, reducing maximum drawdown by 93.1% and attack success rates by 27.2% in testing.

• →AI crypto trading systems face new risks where compromised agents can execute real trades causing irreversible financial losses.
• →SAE framework implements protective middleware with exposure budgets, rate limits, and slippage bounds to prevent catastrophic execution failures.
• →Testing on Binance perpetual futures data showed 93.1% reduction in maximum drawdown and 97.5% improvement in risk metrics.
• →The system addresses supply chain risks from third-party AI skills and tools that could be compromised or malicious.
• →Framework introduces the 'Delegation Gap' metric to measure and test the reliability of AI-powered trading execution.