Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vllm package, versions 0.5.5 up to but not including 0.11.1, is vulnerable to denial of service through the chat completions and tokenize endpoints. An authenticated user can pass specially crafted chat_template_kwargs values, such as one that forces tokenization, which blocks the API server's event loop and delays all other requests. Upgrade to vllm 0.11.1 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 |
|---|---|---|---|---|
| 6.5 | Medium | 3.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0054, the 45th percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:34 UTC First seen by agentprime
- 31 Oct 2026, 14:34 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-69j4-grxj-j64p
- OSV: GHSA-69j4-grxj-j64p
- github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p
- nvd.nist.gov/vuln/detail/CVE-2025-62426
- github.com/vllm-project/vllm/pull/27205
- github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b
- github.com/advisories/GHSA-69j4-grxj-j64p
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2012.yaml
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610
- github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814
- pypi.org/project/vllm