Deserialization in Vllm-project 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: 0.021 (84.5th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 9.1 (Critical). Vector: CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H.
Affected products
- Vllm-project Vllm — versions >= 0.6.5, < 0.8.0
Weakness classification (CWE)
Public proof-of-concept exploits
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7 (x_refsource_CONFIRM)
- https://github.com/vllm-project/vllm/pull/14228 (x_refsource_MISC)
- https://github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2 (x_refsource_MISC)
Frequently asked questions
- What is CVE-2025-29783?
- CVE-2025-29783 is a critical-severity vulnerability in Vllm-project Vllm, classified under Deserialization of Untrusted Data. CVSS score: 9.1/10. Published 2025-03-19.
- How severe is CVE-2025-29783?
- Critical severity. CVSS v3 base score is 9.1 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.