CVE-2026-55574

HIGHNVD 7.57.5
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to NVD's CVSS score.

Score 7.5 from GitHub Security Advisory (severity: HIGH) published 2026-07-17. NVD baseline CVSS 7.5; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, NVD CVSS v3
Trending — 4 sources updated this week

Also known asEUVD-2026-41924 (ENISA EUVD) · GHSA-rwxx-mrjm-wc2m (GitHub Security Advisories)Source: ENISA EUVD

7.5EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.6%CVSS: 7.5Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

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.

CVSS v3
7.5
EG Score
7.5HIGHmedium confidence
EG Risk
34
EG Risk 34/100

EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.

How it’s computed (value × EchelonGraph’s weight)
Severity75% × 45%
Impact severity (EG Severity): CVSS 7.5 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation0.6% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at every mission impact level.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: A fix is available. Apply it within your standard update timelines.
EPSS PROB
0.6%
EPSS %ILE
47th
KEV
Not listed

What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)

The EG score (7.5): severity, escalated by confirmed exploitation. This CVE's 7.5 is its impact severity (EG Severity), not escalated.

EG Severity
7.5 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
0.6% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-31). FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Track at medium mission impactTrack at every mission impact level.CISA BOD 26-04: 60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.

SSVC (CISA's decision table, applied by EchelonGraph)Track at every mission impact level.

A fix is available. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

July 6, 2026

Last Modified

October 25, 2026

Advisory Details (3)

Auto-updated Jul 6, 2026
Patch available. Sources: github_commit, github_pr, github.
GitHub advisoryMentions a patch (unverified)

ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-rwxx-mrjm-wc2m
GitHub pull request

[Security] Add timeout guard for regex compilation in structured outp…

Fix merged in vllm-project/vllm PR #45118 on 2026-06-13 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/45118
GitHub commit

commit 2b3006076c5e (vllm-project/vllm)

Fix landed in vllm-project/vllm commit 2b3006076c5e — awaiting tagged release

https://github.com/vllm-project/vllm/commit/2b3006076c5e9bc4cda9e03e3641388de3c5c286

Vendor Advisories for CVE-2026-55574(14)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Patch Availability(14)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhelai3/disk-image-cuda-rhel9:17909574172026-10-05redhat
redhatrhelai3/bootc-rocm-rhel9:17906144472026-10-05redhat
redhatrhaii/vllm-rocm-rhel9:17901096202026-09-23redhat
redhatrhaii/vllm-cuda-rhel9:17900901312026-09-23redhat
redhatrhaii/vllm-spyre-rhel9:17900761412026-09-23redhat
redhatrhaii/vllm-cpu-rhel9:17900757932026-09-23redhat
redhatrhaii/vllm-cpu-rhel9:17896811282026-09-21redhat
redhatrhaii/vllm-spyre-rhel9:17896812012026-09-21redhat
redhatrhaii/vllm-cuda-rhel9:17896811262026-09-21redhat
redhatrhaii/vllm-rocm-rhel9:17896811262026-09-21redhat
redhatrhaiis/vllm-cuda-rhel9:17878605802026-08-31redhat
redhatrhaiis/vllm-rocm-rhel9:17878848732026-08-31redhat
redhatrhaiis/vllm-spyre-rhel9:17871617762026-08-26redhat
pipvllm @ 0.24.0 (fixes < 0.24.0)—ghsa

Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
vllm0.0.1 ... 0.9.2 (89 versions)
  • every version up to 0.24.0: fixed in 0.24.0
—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 11× in last 7d / 47× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.

Showing the most recent 100 of 188 refreshes on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. None are among the latest 100 rows. The 88 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-02 16:45 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  2. 2026-11-01 16:34 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  3. 2026-11-01 07:43 UTCGHSA enrichmentGHSA-rwxx-mrjm-wc2m · GitHub severity HIGH · GitHub CVSS 7.5
  4. 2026-11-01 07:43 UTCEG score recompute
  5. 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  6. 2026-10-30 16:34 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  7. 2026-10-29 16:33 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  8. 2026-10-28 16:32 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  9. 2026-10-27 21:02 UTCEG score recompute
  10. 2026-10-27 21:02 UTCVendor advisory
  11. 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  12. 2026-10-26 16:31 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  13. 2026-10-25 20:26 UTCEG score recompute
  14. 2026-10-25 20:26 UTCVendor advisory
  15. 2026-10-25 16:33 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  16. 2026-10-25 14:18 UTCEG score recompute
  17. 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  18. 2026-10-24 02:57 UTCEG score recompute
  19. 2026-10-24 02:57 UTCVendor advisory
  20. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  21. 2026-10-22 16:34 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  22. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  23. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  24. 2026-10-19 16:32 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  25. 2026-10-18 16:32 UTCEPSS rescoreEPSS 0.6% · 46th percentile
Show 75 more
  1. 2026-10-18 03:30 UTCEG score recompute
  2. 2026-10-17 16:34 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  3. 2026-10-17 03:17 UTCEG score recompute
  4. 2026-10-17 03:17 UTCVendor advisory
  5. 2026-10-16 16:42 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  6. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  7. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  8. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  9. 2026-10-13 13:54 UTCOSV refresh
  10. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  11. 2026-10-12 15:55 UTCEG score recompute
  12. 2026-10-11 19:39 UTCEG score recompute
  13. 2026-10-11 16:54 UTCEG score recompute
  14. 2026-10-11 14:17 UTCEG score recompute
  15. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  16. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  17. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  18. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  19. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  20. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  21. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  22. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  23. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  24. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  25. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  26. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  27. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  28. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  29. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  30. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  31. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  32. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  33. 2026-09-23 06:23 UTCEG score recompute
  34. 2026-09-23 06:23 UTCVendor advisory
  35. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  36. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  37. 2026-09-18 05:59 UTCEG score recompute
  38. 2026-09-18 05:59 UTCVendor advisory
  39. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  40. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  41. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  42. 2026-09-15 03:11 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  43. 2026-09-14 11:39 UTCVendor advisory
  44. 2026-09-13 23:56 UTCEG score recompute
  45. 2026-09-13 23:56 UTCVendor advisory
  46. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.6% · 46th percentile
  47. 2026-09-13 08:43 UTCEG score recompute
  48. 2026-09-13 08:43 UTCVendor advisory
  49. 2026-09-12 13:36 UTCEG score recompute
  50. 2026-09-12 13:36 UTCVendor advisory
  51. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  52. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  53. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  54. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  55. 2026-09-06 14:10 UTCEG score recompute
  56. 2026-09-06 14:10 UTCVendor advisory
  57. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  58. 2026-09-05 23:07 UTCEG score recompute
  59. 2026-09-05 23:07 UTCVendor advisory
  60. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  61. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  62. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  63. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  64. 2026-08-30 19:48 UTCEG score recompute
  65. 2026-08-30 19:48 UTCVendor advisory
  66. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  67. 2026-08-30 08:01 UTCEG score recompute
  68. 2026-08-30 08:01 UTCVendor advisory
  69. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  70. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  71. 2026-08-27 21:58 UTCEG score recompute
  72. 2026-08-27 21:58 UTCVendor advisory
  73. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.6% · 45th percentile
  74. 2026-08-27 02:12 UTCEG score recompute
  75. 2026-08-27 02:12 UTCVendor advisory

Related CVEs(same product + same vendor + same CWE)

Frequently asked(5)

What is CVE-2026-55574?
CVE-2026-55574 is a high-severity vulnerability; its CVE record was published on July 6, 2026. 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…
When was the CVE record for CVE-2026-55574 published?
The CVE record for CVE-2026-55574 was published on July 6, 2026. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of October 25, 2026; the record at its source may have been updated since.
Is CVE-2026-55574 actively exploited?
CVE-2026-55574 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.6% probability of exploitation in the next 30 days (47th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-55574?
CVE-2026-55574 has a CVSS v3 base score of 7.5 (NVD).
How do I remediate CVE-2026-55574?
A fix for CVE-2026-55574 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-55574 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-55574

Explore →

Is Your Infrastructure Affected by CVE-2026-55574?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Book a Demo →Browse All CVEs