CVSS 4.0
7.7 highCVSS: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:PHigh (7.7) in mlc-ai xgrammar. EPSS 0.5% estimated probability of exploitation activity in the next 30 days. Fixed in xgrammar 0.1.21.
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/E:PCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:Hxgrammar (PyPI): fixed in 0.1.21Explain CVE-2025-57809 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2025-57809?via=ask-ai-copy and https://cve.bz/cve/CVE-2025-57809?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2025-57809 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.
From the NVD's CPE matches.
| Product | Affected |
|---|---|
| mlc-ai:xgrammar | before 0.1.21 |
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-5cmr-4px5-23pc | PyPI | xgrammar | <0.1.21 | 0.1.21 |
| PYSEC-2026-2054 | PyPI | xgrammar | <0.1.21 | 0.1.21 |
Red Hat rates this Important.
This vulnerability is considered Important because it can be exploited remotely, without authentication or user interaction, and directly impacts the availability of systems that rely on xgrammar for structured output parsing. Unlike a Moderate flaw that might require unusual conditions or only cause partial degradation, the infinite recursion issue reliably leads to process termination or complete resource exhaustion when malicious input is supplied. Since xgrammar is often integrated into long-running LLM inference services or API backends, a single crafted grammar can consistently force these services into a denial-of-service state, making it a practical, high-impact attack vector. While it does not compromise confidentiality or integrity, the ease of exploitation, network accessibility, and total loss of availability elevate it from a moderate to an important security issue.
Mitigation is either unavailable or does not meet Red Hat Product Security standards for usability, deployment, applicability, or stability.
| Product | Package | State | Advisory |
|---|---|---|---|
| Red Hat Enterprise Linux AI 1.5 | rhelai1/instructlab-intel-rhel9:1.5.4-1761050413 | Fixed 2025-11-03 | RHSA-2025:19421 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-intel-rhel9:1.5.4-1761060689 | Fixed 2025-11-03 | RHSA-2025:19422 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/instructlab-nvidia-rhel9:1.5.4-1761220254 | Fixed 2025-11-03 | RHSA-2025:19423 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-azure-amd-rhel9:1.5.4-1761073793 | Fixed 2025-11-03 | RHSA-2025:19424 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/instructlab-amd-rhel9:1.5.4-1761043227 | Fixed 2025-11-03 | RHSA-2025:19425 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-gcp-nvidia-rhel9:1.5.4-1761236079 | Fixed 2025-11-03 | RHSA-2025:19426 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-amd-rhel9:1.5.4-1761064179 | Fixed 2025-11-03 | RHSA-2025:19427 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-nvidia-rhel9:1.5.4-1761228838 | Fixed 2025-11-03 | RHSA-2025:19428 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-aws-nvidia-rhel9:1.5.4-1761236150 | Fixed 2025-11-03 | RHSA-2025:19429 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-azure-nvidia-rhel9:1.5.4-1761238736 | Fixed 2025-11-03 | RHSA-2025:19430 |
| Red Hat AI Inference Server | rhaiis/vllm-cuda-rhel9 | Affected | |
| Red Hat AI Inference Server | rhaiis/vllm-rocm-rhel9 | Affected |
Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2025-57809.
The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.