Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions before 0.30.0 contain a resource exhaustion flaw in MooncakeConnector, where rejected prefill requests leave transfer placeholders that are never reclaimed. An attacker who can send requests to the service can repeatedly submit rejected prefill requests to exhaust sender task pools, delaying valid requests by up to 480 seconds while health checks still report success. Upgrade vLLM to version 0.30.0 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 |
|---|---|---|---|---|
| 6.9 | Medium | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0052, the 44th percentile, on 13 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:09 UTC First seen by agentprime
- 31 Oct 2026, 14:09 UTC Confirmed by OSV
Sources
- OSV: PYSEC-2026-4007
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py#L1234-L1242
- www.vulncheck.com/advisories/vllm-through-0.29.0-resource-exhaustion-via-ownerless-mooncake-transfer-placeholders
- github.com/vllm-project/vllm/pull/51236
- github.com/vllm-project/vllm