CVE-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 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.
What this means
- Exposure
- Exploitable remotely over the network, without authentication and with no action from the victim.
- Impact
- An attacker can take the service offline.
- Weakness
- A regular expression blows up on a chosen input and stalls processing (ReDoS).
- Likelihood
- Its EPSS score stays low: nothing points to imminent exploitation, which is no reason to leave it unpatched.
What to doFold into the next patch cycle. Start with the instances exposed to the internet.
Read automatically from the CVSS vector, the weakness type (CWE) and the EPSS score. The technical description above remains the one published by NIST.