PatchSiren cyber security CVE debrief
CVE-2026-94625 vllm-project CVE debrief
CVE-2026-94625 is a resource exhaustion vulnerability in vLLM through version 0.29.0. Rejected prefill requests can create ownerless transfer placeholders that are never reclaimed, causing valid requests to be delayed by up to 480 seconds. Health checks continue returning success despite this issue. Defenders should assess exposure and prioritize verification and remediation efforts. The vulnerability requires verification of vLLM versions and exposure, and remediation priority is high for affected deployments.
- Vendor
- vllm-project
- Product
- vllm
- CVSS
- MEDIUM 6.9
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-09-21
- Original CVE updated
- 2026-09-29
- Advisory published
- 2026-09-21
- Advisory updated
- 2026-09-29
Who should care
Defenders responsible for vLLM deployments, operators of affected platforms, vulnerability management teams, and security teams should assess exposure to this vulnerability and prioritize verification and remediation efforts. They should review the supplied official advisory or CVE record to validate affected scope, severity, and vendor guidance. They should also plan vendor-supported updates or mitigations through normal change control where exposure is
Why it matters
CVE-2026-94625 is a resource exhaustion vulnerability in vLLM through version 0.29.0. Defenders should prioritize verifying the version of vLLM in use and assessing exposure to this vulnerability. If vulnerable, they should apply patches or mitigations as available.
- Valid requests may be delayed by up to 480 seconds.
- Health checks may continue returning success despite the vulnerability.
- The vulnerability requires verification of vLLM versions and exposure.
- Remediation priority is high for affected deployments.
Technical summary
The vulnerability is caused by rejected prefill requests creating ownerless transfer placeholders that are never reclaimed in vLLM through version 0.29.0. This can lead to valid requests being delayed by up to 480 seconds while health checks continue returning success. The issue requires verification of vLLM versions and exposure, and remediation priority is high for affected deployments. Defenders should prioritize verifying the version of vLLM in use and assessing exposure to this vulnerability. If vulnerable, they should apply patches or mitigations as available.
Defensive priority
Defenders should prioritize verifying the version of vLLM in use and assessing exposure to this vulnerability. If vulnerable, they should apply patches or mitigations as available.
Recommended defensive actions
- Verify the version of vLLM in use and assess exposure to this vulnerability.
- Apply patches or mitigations as available.
- Monitor for rejected prefill requests and ownerless transfer placeholders.
- Review health checks for potential false positives.
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up.
- Plan vendor-supported updates or mitigations through normal change control where exposure is confirmed.
- Review compensating controls for exposed systems while remediation is scheduled and verified.
Evidence notes
The CVE record and NVD entry provide details on the vulnerability, including its description and affected versions. However, the corpus does not establish exploitation or impact, and remediation requires verification from the supplied official sources.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-94625 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-94625
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-94625 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-94625
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/vllm-project/vllm
[email protected] - Product
-
Source reference
Unverified legacy reference
URL: https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/mooncake/mooncake_connector.py
[email protected] - Product
-
Source reference
Unverified legacy reference
URL: https://github.com/vllm-project/vllm/pull/51236
[email protected] - Issue Tracking, Patch
-
Source reference
Unverified legacy reference
URL: https://www.vulncheck.com/advisories/vllm-through-0.29.0-resource-exhaustion-via-ownerless-mooncake-transfer-placeholders
[email protected] - Third Party Advisory
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.