Smooth AI criminal drives 'first' end-to-end agentic ransomware attack Sysdig threat researchers identified what they claim is the first known case of agentic ransomware, an attack fully automated by a large language model (LLM) to compromise a production database server, encrypt data, and demand payment. The operation, dubbed JadePuffer, exploited a critical vulnerability in the Langflow platform to execute a coordinated attack that bypassed traditional security measures and adapted in real time to achieve its objectives. The attack began by exploiting CVE-2025-3248, a remote code-execution flaw in Langflow that allows unauthenticated attackers to run arbitrary Python code on the host. Once inside the system, the AI-driven agent scanned for and collected sensitive information, including API keys for cloud providers like Alibaba Cloud, Tencent Cloud, and Huawei Cloud, as well as credentials for AWS, Azure, and Google Cloud Platform. It also targeted cryptocurrency wallets and database credentials, demonstrating a broad scope of reconnaissance. JadePuffer then established persistence by installing a crontab entry on the Langflow server, ensuring it could maintain access and communicate with the attacker’s infrastructure every 30 minutes. The AI agent’s next target was a separate production server running a MySQL database and an Alibaba Nacos configuration service. Nacos, an open-source service-discovery platform, was exploited using multiple vectors, including an authorization bypass flaw (CVE-2021-29441) and forged JSON web tokens (JWTs) generated with the default signing key. The LLM-powered agent used its root-level database access to inject a backdoor administrator into the Nacos database, enabling full control over the system.#tencent_cloud #aws #alibaba_cloud #langflow #huawei_cloud
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
An AI Just Carried Out a Cyber Attack Without Any Human Oversight for the First Time Security researchers have uncovered what they believe to be the first documented instance of an artificial intelligence agent executing a cyber attack from start to finish without human assistance. The incident, involving an AI named Jadepuffer, marks a significant milestone in both artificial intelligence and cyber security, raising alarms about the growing threat posed by autonomous AI systems. The attack, which occurred on July 3, 2026, involved an AI-driven ransomware campaign that bypassed human oversight entirely, demonstrating the potential for AI to execute complex cyber operations at unprecedented speeds. The AI-powered attack targeted a vulnerable server, where it gained access by exploiting weak security protocols. Once inside, the system obtained login credentials and encrypted a production database, demanding a bitcoin ransom from the victim. Researchers from cloud security firm Sysdig described the process as a "complete extortion operation driven end-to-end by a large language model (LLM)." The AI, which they named Jadepuffer, adapted its tactics in real-time, refining its approach to overcome failed attempts within seconds. For example, it transitioned from a failed login to a successful breach in just 31 seconds, showcasing its ability to learn and adjust strategies on the fly. The attack’s autonomy was further highlighted by its use of an open-source tool called Langflow, which the AI leveraged to search for credentials, specifically targeting Chinese providers such as Alibaba, Tencent, and Huawei. This level of precision and efficiency far exceeds the capabilities of traditional ransomware attacks, which typically rely on human operators to execute and modify tactics.#tencent #alibaba #jadepuffer #sysdig #langflow
