Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vLLM package, versions before 0.24.0, passes user-supplied regex strings from the structured_outputs.regex API parameter to the xgrammar and outlines grammar backends without a compilation timeout. An attacker who can send inference requests can submit a pattern that causes exponential state-space blowup, hanging an inference worker indefinitely (denial of service). Upgrade to vLLM 0.24.0 or later, which contains the fix.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 8.7 | High | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0058, the 48th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:10 UTC First seen by agentprime
- 31 Oct 2026, 14:10 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-rwxx-mrjm-wc2m
- OSV: GHSA-rwxx-mrjm-wc2m
- github.com/vllm-project/vllm/security/advisories/GHSA-rwxx-mrjm-wc2m
- nvd.nist.gov/vuln/detail/CVE-2026-55574
- github.com/vllm-project/vllm/pull/45118
- github.com/vllm-project/vllm/commit/2b3006076c5e9bc4cda9e03e3641388de3c5c286
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2304.yaml
- github.com/vllm-project/vllm