Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vLLM package, versions 0.6.5 up to but not including 0.8.0, is vulnerable when configured to use the Mooncake KV transfer integration. Its ZMQ-over-TCP socket passes network data directly to Python pickle deserialization, and the source says there are no network or authentication controls on that path. An attacker who can reach the service over the network may be able to execute arbitrary code on the affected hosts. Upgrade vLLM to version 0.8.0 or later.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 9.1 | Critical | 3.1 | CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0073, the 55th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:40 UTC First seen by agentprime
- 31 Oct 2026, 14:40 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-x3m8-f7g5-qhm7
- OSV: GHSA-x3m8-f7g5-qhm7
- github.com/vllm-project/vllm/security/advisories/GHSA-x3m8-f7g5-qhm7
- nvd.nist.gov/vuln/detail/CVE-2025-29783
- github.com/vllm-project/vllm/pull/14228
- github.com/vllm-project/vllm/commit/288ca110f68d23909728627d3100e5a8db820aa2
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-63.yaml
- github.com/vllm-project/vllm