Federal Agencies Under Attack: Critical MLflow Vulnerability Exploited by Hackers
The US Cybersecurity and Infrastructure Security Agency (CISA) has issued a warning to federal agencies that threat actors are actively exploiting a critical vulnerability in the popular AI engineering platform, MLflow. The agency has added this flaw to its catalog of exploited vulnerabilities and ordered all U.S. Federal Civilian Executive Branch (FCEB) agencies to secure their MLflow instances within two weeks.
MLflow is an open-source platform used by thousands of organizations worldwide, including government agencies, to manage and optimize large language models (LLMs) and agents. The vulnerability, tracked as CVE-2026-64849, allows attackers to remotely access internal services or cloud metadata configurations on unpatched instances without any privileges. This is done through a DNS-rebinding server-side request forgery (SSRF) bypass in MLflow’s outbound webhook delivery.
According to the CISA warning, the vulnerability is exposed due to the default configuration of MLflow’s Tracking Server, which leaves the model-registry webhooks API unauthenticated. This allows an attacker who can reach the tracking server to issue HTTP requests to arbitrary internal or cloud endpoints and read the responses, effectively stealing sensitive information such as AWS Identity and Access Management (IAM) credentials.
The attack is relatively low-complexity and can be automated for large-scale attacks. Cybersecurity firm watchTowr has revealed that attackers began scanning for MLflow systems within hours of the CVE ID being assigned, indicating a coordinated effort to exploit this vulnerability.
This latest warning from CISA comes on the heels of several other critical vulnerabilities being exploited in the wild, including a remote code execution (RCE) flaw in Windows IKE Service Extensions and a Windows Task Host flaw. The agency has emphasized the importance of prioritizing patching and reviewing audit logs for signs of compromise to prevent sensitive information from being exfiltrated.
If your organization runs MLflow, it’s essential to take immediate action to secure your systems. This includes patching any exposed instances, reviewing audit logs for suspicious activity, and checking whether sensitive credentials may have been compromised. By taking proactive measures to address this vulnerability, you can help prevent attackers from exploiting it and protect your organization’s valuable data.
As the cybersecurity landscape continues to evolve, it’s crucial for organizations to stay vigilant and prioritize patching critical vulnerabilities as soon as they are discovered. By doing so, we can reduce the risk of successful attacks and keep our digital assets secure.
Source: Bleeping Computer — 2026-08-20