PatchSiren cyber security CVE debrief
CVE-2026-73559 vllm-project CVE debrief
CVE-2026-73559 is a vulnerability in vLLM, an inference and serving engine for large language models, which allows an authenticated API client to exhaust system resources with a single request. The issue, fixed in version 0.26.0, affects vLLM from version 0.19.0 to 0.25.0. Defenders should assess exposure, prioritize remediation, and verify system inventory.
- Vendor
- vllm-project
- Product
- vllm
- CVSS
- MEDIUM 6.5
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-08-13
- Original CVE updated
- 2026-09-09
- Advisory published
- 2026-08-13
- Advisory updated
- 2026-09-09
Who should care
System administrators and security teams responsible for large language model serving engines should assess exposure, prioritize remediation, and verify system inventory to mitigate potential resource exhaustion attacks. They should also review system logs for potential exploitation attempts and ensure system updates to version 0.26.0 or later are applied.
Why it matters
CVE-2026-73559 allows an authenticated API client to exhaust system resources with a single request, affecting vLLM versions 0.19.0 to 0.25.0. Defenders should assess exposure, prioritize remediation, and verify system inventory.
- Resource exhaustion through CPU and memory consumption
- Potential denial of service through async scheduling capacity depletion
- Engine request slot and response buffering exhaustion
Technical summary
The /v1/completions endpoint in vLLM accepts an unbounded list of strings or lists of integers, which can be used to exhaust system resources. The issue is fixed in version 0.26.0. An authenticated API client can exploit this vulnerability to consume excessive CPU, memory, async scheduling capacity, engine request slots, and response buffering with a single request, affecting vLLM versions 0.19.0 to 0.25.0. Defenders should focus on updating to version 0.26.0 or later and monitoring system resource utilization closely.
Defensive priority
Medium priority for system administrators and security teams to assess and remediate
Recommended defensive actions
- Assess exposure by checking system inventory for vLLM versions 0.19.0 to 0.25.0
- Prioritize remediation for affected systems
- Verify system updates to version 0.26.0 or later
- Review compensating controls for exposed systems while remediation is scheduled and verified
- Check relevant monitoring, detection, and logs for exposed assets that need extra review
- Track exceptions, retest remediated assets, and close the item only after evidence is documented
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
Evidence notes
The CVE record and NVD entry provide details on the vulnerability, affected versions, and fixed version. The vulnerability allows an authenticated API client to exhaust system resources with a single request, affecting vLLM versions 0.19.0 to 0.25.0. Defenders should assess exposure, prioritize remediation, and verify system inventory. Evidence limits suggest verifying system updates to version 0.26.0 or later and reviewing system logs for potential exploitation attempts.
Sources and references
Verified primary and authoritative sources
-
CVE-2026-73559 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2026-73559
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2026-73559 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2026-73559
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/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
-
Source reference
Unverified legacy reference
URL: https://github.com/vllm-project/vllm/pull/47845
-
Source reference
Unverified legacy reference
URL: https://github.com/vllm-project/vllm/releases/tag/v0.26.0
-
Source reference
Unverified legacy reference
URL: https://github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
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.