Agentic AI Used to Conduct Ransomware Attack via Langflow A threat actor exploited a critical vulnerability in the open-source Langflow framework to execute an agentic ransomware attack, according to a report by cloud security firm Sysdig. The attack, attributed to a group dubbed JadePuffer, leveraged a flaw in Langflow—a Python-based tool for building large language model (LLM)-driven applications—to gain unauthorized access to an organization’s systems and deploy ransomware. The breach highlights the growing risks posed by AI-driven cyber operations and the vulnerabilities in widely used open-source tools. The attack began when JadePuffer exploited CVE-2025-3248, a critical authentication flaw in Langflow disclosed in April 2025. This vulnerability, which received a CVSS score of 9.8, allowed attackers to execute arbitrary Python code on the host running Langflow. The U.S. Cybersecurity and Infrastructure Security Agency (CISA) flagged the flaw as being actively exploited in early May. By exploiting this vulnerability, the threat actor gained code execution privileges, enabling them to probe the system for sensitive information. During the initial phase of the attack, JadePuffer used the LLM to conduct reconnaissance, scanning the network for secrets such as API keys, cloud credentials, cryptocurrency wallets, configuration files, and database credentials. The attackers then dumped the Postgres database hosted by Langflow to extract these secrets, scanned internal network addresses, and identified MinIO services for further credential extraction. A cron job was deployed to maintain persistent access to the Langflow server. Notably, the LLM adapted its actions in real time to complete tasks, extract credentials from different file types, and log into discovered endpoints.#langflow #jadepuffer #sysdig #cisa #nacos
