Deserialization in Vllm
CVE-2025-29783
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 r…
Vulnerability class: Insecure Deserialization
EPSS: 0.008 (53.2th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 9.0 (Critical). Vector: CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H.
Affected products
- Vllm
- Vllm-project Vllm — versions >= 0.6.5, < 0.8.0
Weakness classification (CWE)
Public proof-of-concept exploits
References
- security-advisories@github.com (x_refsource_CONFIRM, Vendor Advisory)
- security-advisories@github.com (x_refsource_MISC, Issue Tracking, Vendor Advisory)
- security-advisories@github.com (Patch, x_refsource_MISC)
Frequently asked questions
- What is CVE-2025-29783?
- CVE-2025-29783 is a critical-severity vulnerability in Vllm, classified under Deserialization of Untrusted Data. CVSS score: 9.0/10. Published 2025-03-19.
- How severe is CVE-2025-29783?
- Critical severity. CVSS v3 base score is 9.0 out of 10.
- Is CVE-2025-29783 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.