Skip to main content

Deserialization of Untrusted Data

CVE-2025-32444

High
9.8/10

Summary

The vLLM package is a high-throughput and memory-efficient inference and serving engine for large language models (LLMs). Versions 0.6.5 through 0.8.4, when using Mooncake integration, are vulnerable to Remote Code Execution (RCE) due to the use of Pickle-based serialization over unsecured ZeroMQ sockets. The affected ZeroMQ sockets are configured to listen on all network interfaces, significantly increasing the likelihood that an attacker can access them remotely to exploit the vulnerability. It is important to note that vLLM instances not using Mooncake integration are not affected by this issue.

  • LOW
  • NETWORK
  • HIGH
  • UNCHANGED
  • NONE
  • NONE
  • HIGH
  • HIGH

CWE-502 - Deserialization of Untrusted Data

Deserialization of untrusted data vulnerabilities enable an attacker to replace or manipulate a serialized object, replacing it with malicious data. When the object is deserialized at the victim's end the malicious data is able to compromise the victim’s system. The exploit can be devastating, its impact may range from privilege escalation, broken access control, or denial of service attacks to allowing unauthorized access to the application's internal code and logic which can compromise the entire system.

References

Advisory Timeline

  • Published