Thursday, January 30, 2025
HomeArtificial IntelligenceOllama AI Platform Flaw Let Attackers Execute Remote Code

Ollama AI Platform Flaw Let Attackers Execute Remote Code

Published on

SIEM as a Service

Follow Us on Google News

⁤Hackers attack AI infrastructure platforms since these systems contain a multitude of valuable data, algorithms that are sophisticated in nature, and significant computational resources. ⁤

⁤So, compromising such platforms provides hackers with access to proprietary models and sensitive information, and not only that, it also gives the ability to manipulate the outcomes of AI. ⁤

⁤Cybersecurity researchers at Wiz Research recently discovered an Ollama AI infrastructure platform flaw that enables threat actors to execute remote code. ⁤

Ollama AI Platform Flaw

The critical Remote Code Execution vulnerability has been tracked as “CVE-2024-37032” (“Probllama”), in Ollama which is a popular open-source project for AI model deployment with more than 70,000 GitHub stars.

Free Webinar on API vulnerability scanning for OWASP API Top 10 vulnerabilities -> Book Your Spot

This vulnerability has been responsibly disclosed and mitigated. Users are encouraged to update to Ollama version 0.1.34 or later for their safety.

By June 10, numerous internet-facing Ollama instances were still utilizing vulnerable versions, which highlights the need for users to patch their installations to protect them from potential attacks that exploit this security hole.

Tools of this kind often lack such standard security features as authentication and consequently can be attacked by threat actors.

Over 1000 Ollama instances were exposed, and various AI models were hosted without protection.

Wiz researchers determined in the Ollama server, that leads to arbitrary file overwrites and remote code execution. This issue is especially severe on Docker installations operating under root privileges.

The vulnerability is due to insufficient input validation in the/api/pull endpoint, which allows for path traversal via malicious manifest files from private registries. This highlights the need for enhanced AI security measures.

This critical vulnerability allows for the manifestation of malicious descriptive files using path traversal to enable arbitrary reading and writing of files. ⁤

⁤In Docker installations with root privileges, this can escalate into remote code execution by tampering with /etc/ld.so.preload to load a malicious shared library. ⁤

⁤The attack starts when the /api/chat endpoint is queried, creating a new process that loads the attacker’s payload. ⁤

⁤Even non-root installations are still at risk, as some other exploits utilize the Arbitrary File Read technique.

However, it’s been recommended that the security teams should immediately update Ollama instances and avoid exposing them to the internet without authentication. 

While Linux installations bind to localhost by default, Docker deployments expose the API server publicly, which significantly increases the risk of remote exploitation. 

This highlights the need for robust security measures in rapidly evolving AI technologies.

Disclosure Timeline

  • May 5, 2024 – Wiz Research reported the issue to Ollama.
  • May 5, 2024 – Ollama acknowledged the receipt of the report. 
  • May 5, 2024 – Ollama notified Wiz Research that they committed a fix to GitHub. 
  • May 8, 2024 – Ollama released a patched version. 
  • June 24, 2024 – Wiz Research published a blog about the issue.

Free Webinar! 3 Security Trends to Maximize MSP Growth -> Register For Free

Gurubaran
Gurubaran
Gurubaran is a co-founder of Cyber Security News and GBHackers On Security. He has 10+ years of experience as a Security Consultant, Editor, and Analyst in cybersecurity, technology, and communications.

Latest articles

Hackers Exploiting DNS Poisoning to Compromise Active Directory Environments

A groundbreaking technique for Kerberos relaying over HTTP, leveraging multicast poisoning, has been recently...

New Android Malware Exploiting Wedding Invitations to Steal Victims WhatsApp Messages

Since mid-2024, cybersecurity researchers have been monitoring a sophisticated Android malware campaign dubbed "Tria...

500 Million Proton VPN & Pass Users at Risk Due to Memory Protection Vulnerability

Proton, the globally recognized provider of privacy-focused services such as Proton VPN and Proton...

Arcus Media Ransomware Strikes: Files Locked, Backups Erased, and Remote Access Disabled

The cybersecurity landscape faces increasing challenges as Arcus Media ransomware emerges as a highly...

API Security Webinar

Free Webinar - DevSecOps Hacks

By embedding security into your CI/CD workflows, you can shift left, streamline your DevSecOps processes, and release secure applications faster—all while saving time and resources.

In this webinar, join Phani Deepak Akella ( VP of Marketing ) and Karthik Krishnamoorthy (CTO), Indusface as they explores best practices for integrating application security into your CI/CD workflows using tools like Jenkins and Jira.

Discussion points

Automate security scans as part of the CI/CD pipeline.
Get real-time, actionable insights into vulnerabilities.
Prioritize and track fixes directly in Jira, enhancing collaboration.
Reduce risks and costs by addressing vulnerabilities pre-production.

More like this

Hackers Exploiting DNS Poisoning to Compromise Active Directory Environments

A groundbreaking technique for Kerberos relaying over HTTP, leveraging multicast poisoning, has been recently...

New Android Malware Exploiting Wedding Invitations to Steal Victims WhatsApp Messages

Since mid-2024, cybersecurity researchers have been monitoring a sophisticated Android malware campaign dubbed "Tria...

500 Million Proton VPN & Pass Users at Risk Due to Memory Protection Vulnerability

Proton, the globally recognized provider of privacy-focused services such as Proton VPN and Proton...