CVE-2026-55574
published 2026-07-06CVE-2026-55574: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a…
PriorityP343high7.5CVSS 3.1
AVNACLPRNUINSUCNINAH
EPSS
0.58%
45.5th percentile
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.
Affected
25 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| rhaii | vllm-cpu-rhel9 | — | — |
| rhaii | vllm-cuda-rhel9 | — | — |
| rhaii | vllm-gaudi-rhel9 | — | — |
| rhaii | vllm-neuron-rhel9 | — | — |
| rhaii | vllm-rocm-rhel9 | — | — |
| rhaii | vllm-spyre-rhel9 | — | — |
| rhaii | vllm-tpu-rhel9 | — | — |
| rhaiis | vllm-cpu-rhel9 | — | — |
| rhaiis | vllm-cuda-rhel9 | — | — |
| rhaiis | vllm-neuron-rhel9 | — | — |
| rhaiis | vllm-rocm-rhel9 | — | — |
| rhaiis | vllm-spyre-rhel9 | — | — |
| rhaiis | vllm-tpu-rhel9 | — | — |
| rhelai3 | bootc-aws-cuda-rhel9 | — | — |
| rhelai3 | bootc-azure-cuda-rhel9 | — | — |
| rhelai3 | bootc-azure-rocm-rhel9 | — | — |
| rhelai3 | bootc-cuda-rhel9 | — | — |
| rhelai3 | bootc-gaudi-rhel9 | — | — |
| rhelai3 | bootc-gcp-cuda-rhel9 | — | — |
| rhelai3 | bootc-rocm-rhel9 | — | — |
| rhoai | odh-llm-d-kv-cache-rhel9 | — | — |
| rhoai | odh-vllm-gaudi-rhel9 | — | — |
| vllm-project | vllm | < 0.26.0 | 0.26.0 |
| vllm | vllm | < 0.24.0 | 0.24.0 |
| vllm | vllm | >= 0 < 0.24.0 | 0.24.0 |
CVSS provenance
nvdv3.17.5HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
nvdv4.08.7HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vendor_redhat7.5HIGH
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
GHSA
vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
ghsa·2026-07-17
CVE-2026-55574 [HIGH] CWE-1333 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
## Summary
The `structured_outputs.regex` API parameter passes a user-supplied regex string directly to grammar compiler backends with no compilation timeout. In the xgrammar backend, the string reaches `compile_regex()` with no guard. In the outlines backend, `validate_regex_is_buildable()` blocks structural issues (lookarounds, backreferences) but provides zero protection against exponential DFA state-space explosion. Patterns like `(a+)+b` pass all checks and hang the inference worker.
## Root Cause
`backend_xgrammar.py:91` — no timeout:
```python
ctx = self.compiler.compile_regex(grammar_spec)
```
`backend_outlines.py:299–330` — structural checks only, no complexity analysis:
```pyt
VulDB
vllm-project vLLM up to 0.23.x xgrammar Backend/outlines Backend structured_outputs.regex incorrect regex
vuldb·2026-07-06·CVSS 8.7
CVE-2026-55574 [HIGH] vllm-project vLLM up to 0.23.x xgrammar Backend/outlines Backend structured_outputs.regex incorrect regex
A vulnerability labeled as problematic has been found in vllm-project vLLM up to 0.23.x. The impacted element is an unknown function of the file structured_outputs.regex of the component xgrammar Backend/outlines Backend. Such manipulation leads to incorrect regular expression.
This vulnerability is documented as CVE-2026-55574. The attack can be executed remotely. There is not any exploit available.
Red Hat
vllm: vLLM: Denial of Service via adversarial regular expression in structured outputs API
vendor_redhat·2026-07-06·CVSS 7.5
CVE-2026-55574 [HIGH] CWE-1333 vllm: vLLM: Denial of Service via adversarial regular expression in structured outputs API
vllm: vLLM: Denial of Service via adversarial regular expression in structured outputs API
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service
No detection rules found.
No public exploits indexed.
2026-07-06
Published