CVE-2025-29783
Vllm remote code execution
- Published19 Mar 2025
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.
CVSS 3.1 breakdown
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:HAffected products
Remediation
References
Related CVEs
Recent high-severity vulnerabilities sharing a weakness type.
Frequently asked
Is CVE-2025-29783 being actively exploited?
CVE-2025-29783 is not in the CISA KEV catalog. Its EPSS exploit probability is 0.73%.
How severe is CVE-2025-29783?
CVE-2025-29783 has a CVSS 3.1 base score of 9.0, rated critical. EPSS estimates a 0.73% probability of exploitation.
Which products are affected by CVE-2025-29783?
Affected products include Vllm.
How do I fix CVE-2025-29783?
Upgrade affected software to a fixed version, for example Vllm 0.8.0 or later, then confirm no affected versions remain in your inventory.
How Secuno handles this
Secuno correlates vulnerabilities like CVE-2025-29783 against the real software inventory on every managed device, as each hourly inventory arrives. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.
Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.