CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
Attackers can cause denial of service in vLLM by submitting adversarial regular expressions that hang inference workers due to missing compilation timeouts.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-55574?
CVE-2026-55574 is a high-severity denial of service vulnerability in Vllm Vllm, published on 6 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-1333
Which versions are affected by CVE-2026-55574?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | All versions | 0.24.0 |
vllm PyPI | All versions | 0.24.0 |
vllm PyPI | All versions | 0.24.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-55574?
Upgrade vllm to 0.24.0 or later.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-55574 being exploited?
There is no known exploitation of CVE-2026-55574 in the wild and no public exploit code.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-rwxx-mrjm-wc2m, MINI-3j92-96r2-cxwv, MINI-4m6m-jpm9-4v27, MINI-wqf2-7389-p943, PYSEC-2026-2304.