| Component | vLLM |
| Severity | medium (CVSS 5.3) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L |
| Published (NVD) | 2026-08-13 |
| Last modified | 2026-09-28 |
| Affected versions | vllm < 0.26.0 |
| Fixed in | 0.26.0 |
| Weakness | CWE-400CWE-1333 |
| CISA KEV | not listed |
NVD description
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.
What to do
- Upgrade vLLM to
0.26.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2026-73556
- https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v
- https://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577
- https://github.com/vllm-project/vllm/pull/47595
- https://github.com/vllm-project/vllm/releases/tag/v0.26.0
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...