Robust security is critical in open networks where software controls user funds. Security strategies must evolve as AI’s role ...
EVMbench is OpenAI’s attempt to see whether modern AI systems are up to the task of helping prevent smart contract issues.
OpenAI and Paradigm unveil EVMbench, a benchmark testing AI agents on smart contract security across 120 high-severity vulnerabilities.
Algorand warns developers that vibe coding smart contracts with AI tools risks irreversible fund loss and calls for disciplined agentic engineering.
Yet, despite such optimism, something unreal happened soon after OpenAI launched EVMbench. An exploit involving Claude Opus 4 ...
AI agents are now being tested against real smart contract vulnerabilities after $3.4 billion was lost to crypto hacks in 2025 ...