CVE-2026-130685
vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token ID
Description
vLLM from 0.28.0 before 0.33.0 contains an improper input validation vulnerability that allows unauthenticated attackers to crash the shared EngineCore by sending out-of-range prompt token ids when served with --skip-tokenizer-init. Attackers can submit a large positive token id to /v1/completions, /v1/embeddings, or /pooling, bypassing the tokenizer-gated vocab check and causing a fatal embedding index error that denies service to all tenants.
INFO
Published Date :
Nov. 18, 2026, 11:33 a.m.
Last Modified :
Nov. 18, 2026, 11:33 a.m.
Remotely Exploit :
Yes !
Source :
VulnCheck
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | HIGH | MITRE-CVE | ||||
| CVSS 4.0 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 |
Solution
- Update vLLM to version 0.33.0 or newer.
- Ensure --skip-tokenizer-init is not used if running older versions.
- Validate token IDs for out-of-range values.
- Implement robust input validation for token IDs.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-130685 vulnerability anywhere in the article.