Skip to content
  • Blog Home
  • Cyber Map
  • About Us – Contact
  • Disclaimer
  • Terms and Rules
  • Privacy Policy
Cyber Web Spider Blog – News

Cyber Web Spider Blog – News

Globe Threat Map provides a real-time, interactive 3D visualization of global cyber threats. Monitor DDoS attacks, malware, and hacking attempts with geo-located arcs on a rotating globe. Stay informed with live logs and archive stats.

  • Home
  • Cyber Map
  • Cyber Security News
  • Security Week News
  • The Hacker News
  • How To?
  • Toggle search form

vLLM Vulnerability Enables Remote Code Execution Via Malicious Payloads

Posted on November 24, 2025November 24, 2025 By CWS

A crucial reminiscence corruption vulnerability in vLLM variations 0.10.2 and later permits attackers to attain distant code execution by way of the Completions API endpoint by sending maliciously crafted immediate embeddings.

The vulnerability resides within the tensor deserialization course of inside vLLM’s entrypoints/renderer.py at line 148.

When processing user-supplied immediate embeddings, the system hundreds serialized tensors utilizing torch.load() with out ample validation checks.

The Vulnerability Defined

A change launched in PyTorch 2.8.0 disabled sparse tensor integrity checks by default, creating an assault vector for malicious actors.

With out correct validation, attackers can craft tensors that bypass inner bounds checks, triggering an out-of-bounds reminiscence write in the course of the to_dense() conversion.

This reminiscence corruption could cause the vLLM server to crash and probably allow arbitrary code execution inside the server course of.

AttributeDetailsCVE IDCVE-2025-62164SeverityHighCVSS Score8.8/10Affected ProductvLLM (pip)Affected Variations≥ 0.10.2

This vulnerability impacts all deployments working vLLM as a server, notably these deserializing untrusted or model-provided payloads.

Any consumer with API entry can exploit this flaw to attain denial-of-service circumstances and probably achieve distant code execution capabilities.

The assault requires no particular privileges, making it accessible to each authenticated and unauthenticated customers, relying on the API configuration.

Organizations utilizing vLLM in manufacturing environments, cloud deployments, or shared infrastructure face vital threat, as profitable exploitation may compromise your entire server and adjoining methods.

The vLLM undertaking has addressed this vulnerability in pull request #27204. Customers ought to instantly improve to the patched model.

As a brief mitigation, directors ought to limit API entry to trusted customers solely and implement enter validation layers that examine immediate embeddings earlier than they attain the vLLM processing pipeline.

The vulnerability was found and responsibly disclosed by the AXION Safety Analysis Group, highlighting the significance of coordinated vulnerability disclosure within the AI infrastructure ecosystem.

Observe us on Google Information, LinkedIn, and X for day by day cybersecurity updates. Contact us to function your tales.

Cyber Security News Tags:Code, Enables, Execution, Malicious, Payloads, Remote, vLLM, Vulnerability

Post navigation

Previous Post: Beware of North Korean Fake Job Platform Targeting U.S. Based AI-Developers
Next Post: Hackers Replace ‘m’ with ‘rn’ in Microsoft(.)com to Steal Users’ Login Credentials

Related Posts

Threat Actors Weaponizing Facebook and Google Ads as Financial Platforms to Steal Sensitive Data Cyber Security News
Seraphic Browser-Native Protection Now Available for Purchase on the CrowdStrike Marketplace Cyber Security News
Securing Multi-Cloud Infrastructures in 2025 Enterprise Deployments Cyber Security News
RondoDox Botnet Exploits 50+ Vulnerabilities to Attack Routers, CCTV Systems and Web Servers Cyber Security News
Authorities Dismanteled Major Credit Card Fraud Operation Impacting 4.3 Million Cardholders Cyber Security News
Critical ASP.NET Vulnerability Allows Attacker To Bypass Security Feature Remotely Cyber Security News

Categories

  • Cyber Security News
  • How To?
  • Security Week News
  • The Hacker News

Recent Posts

  • PoC released for W3 Total Cache Vulnerability that Exposes 1+ Million Websites to RCE Attacks
  • CISA Confirms Exploitation of Recent Oracle Identity Manager Vulnerability
  • CrowdStrike Insider Helped Hackers Falsely Claim System Breach
  • New Fluent Bit Flaws Expose Cloud to RCE and Stealthy Infrastructure Intrusions
  • APT35 Hacker Groups Internal Documents Leak Exposes their Targets and Attack Methods

Pages

  • About Us – Contact
  • Disclaimer
  • Privacy Policy
  • Terms and Rules

Archives

  • November 2025
  • October 2025
  • September 2025
  • August 2025
  • July 2025
  • June 2025
  • May 2025

Recent Posts

  • PoC released for W3 Total Cache Vulnerability that Exposes 1+ Million Websites to RCE Attacks
  • CISA Confirms Exploitation of Recent Oracle Identity Manager Vulnerability
  • CrowdStrike Insider Helped Hackers Falsely Claim System Breach
  • New Fluent Bit Flaws Expose Cloud to RCE and Stealthy Infrastructure Intrusions
  • APT35 Hacker Groups Internal Documents Leak Exposes their Targets and Attack Methods

Pages

  • About Us – Contact
  • Disclaimer
  • Privacy Policy
  • Terms and Rules

Categories

  • Cyber Security News
  • How To?
  • Security Week News
  • The Hacker News

Copyright © 2025 Cyber Web Spider Blog – News.

Powered by PressBook Masonry Dark