Agentic finance security: are your controls keeping up?

TL;DR: The Moonwell exploit and OpenAI's EVMBench show that AI agents are currently better at exploiting smart contract flaws than detecting or patching them, according to ClawSecure, which matters because autonomous systems are already handling real capital and can turn small logic errors into immediate financial loss. Defensive controls now need to verify intent, not just patterns.

Editorial analysis by NHI Mgmt Group, based on content published by ClawSecure: “When AI Writes the Code That Moves Your Money: Lessons from the Moonwell Exploit and OpenAI's EVMBench”.

By the numbers:

• The Moonwell exploit cost $1.78 million after a pricing formula valued cbETH at $1.12 instead of roughly $2,200.
• OpenAI's GPT-5.3-Codex achieved a 72.2% success rate in exploit mode but performed substantially worse at detection and patching.

Key questions

Q: What breaks when agentic systems can move money before humans review the decision?

A: The control breaks at the point where a wrong conclusion becomes an irreversible action.

Q: Why do AI agents create more risk than traditional automation?

A: AI agents create more risk because they can interpret context, choose actions, and invoke tools autonomously.

Q: How do teams know whether agentic delivery controls are actually working?

A: Look for evidence that every important action is mediated, recorded, and bounded.

Practitioner guidance

• Audit autonomous financial workflows for authority boundaries Map where AI or code can value assets, move funds, or trigger liquidations without a fresh human decision, then reduce those paths to task-scoped authority.
• Require intent checks before execution For pricing, trading, or liquidation logic, validate that the system's output matches the intended calculation and fails closed when context is incomplete.
• Separate exploit testing from patch testing Test whether your controls can detect abuse as well as they can repair defects, because a system that can exploit faster than it can defend needs tighter runtime restrictions.

Bottom line: The article shows that agentic systems can be better at exploiting financial logic flaws than defending against them.

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →