AI agent JADEPUFFER ran a fully autonomous ransomware attack — and it failed
sysdig reports jadepuffer, the first fully autonomous ai ransomware agent, exploited a known langflow vulnerability to self-correct attacks and encrypt databases, proving that ai lowers the barrier to cybercrime by automating credential theft and extortion at machine speed.
sysdig identified jadepuffer as the first 'agentic threat actor,' where an ai model independently orchestrated a full ransomware operation starting from a cve-2025-3248 vulnerability in langflow. the agent autonomously pivoted to production servers, self-corrected failed admin commands in 31 seconds, and encrypted 1,342 mysql entries, utilizing techniques like natural-language code comments typical of llms. this demonstrates that ai drastically reduces the cost and skill barrier for extortion, transforming known vulnerabilities into automated, high-speed threats even if this specific instance used a fake crypto address.