CVE-2026-54235

MEDIUMNVD 6.56.5
EchelonGraph scoreMEDIUM confidence

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

This medium-severity CVE scores 6.5 under NVD CVSS v3. EPSS exploit probability: 0.4% (39th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, NVD CVSS v3
Trending — 3 sources updated this week

Also known asEUVD-2026-38402 (ENISA EUVD) · GHSA-7h4p-rffg-7823 (GitHub Security Advisories)Source: ENISA EUVD

6.5EG
EchelonGraph verdictMonitorRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (the SSVC decision on this page).
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.4%CVSS: 6.5Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.

CVSS v3
6.5
EG Score
6.5MEDIUMmedium confidence
EG Risk
44
EG Risk 44/100

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)
Severity65% × 45%
Impact severity (EG Severity): CVSS 6.5 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation0.4% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability100% × 15%
CISA's SSVC Automatable value: yes (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Attend at high (mission-essential systems).
Exploitation none (CISA Vulnrichment) · Automatable yes (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 at low or medium mission impact and sooner than that at high.
EPSS PROB
0.4%
EPSS %ILE
39th
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 (6.5): severity, escalated by confirmed exploitation. This CVE's 6.5 is its impact severity (EG Severity), not escalated.

EG Severity
6.5 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.NVD CVSS v3 · CVSS v3.0 or v3.1
EG Likelihood
0.4% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-28). 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 low or medium mission impact; Attend at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; 60 days 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 low or medium mission impact; Attend at high (mission-essential systems).

A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.

Exploitation none (CISA Vulnrichment) · Automatable yes (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)14 days if the affected system is publicly exposed; 60 days if it is not.

The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable yes (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

June 17, 2026

Last Modified

October 25, 2026

Advisory Details (3)

Auto-updated Jun 23, 2026
Patch available. Sources: github_commit, github_pr, github.
GitHub advisoryMentions a patch (unverified)

temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-7h4p-rffg-7823
GitHub pull request

[Security] Reject non-finite temperature and repetition_penalty values

Fix merged in vllm-project/vllm PR #45116 on 2026-06-11 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/45116
GitHub commit

commit d598d239737c (vllm-project/vllm)

Fix landed in vllm-project/vllm commit d598d239737c — awaiting tagged release

https://github.com/vllm-project/vllm/commit/d598d239737cfa37bcfcb98886ec3f3557fc7198

Patch Availability(5)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhaiis/vllm-cuda-rhel9:17878605802026-08-31redhat
redhatrhaiis/vllm-rocm-rhel9:17878848732026-08-31redhat
redhatrhaiis/vllm-rocm-rhel9:17829512442026-07-06redhat
redhatrhaiis/vllm-cuda-rhel9:17829510122026-07-06redhat
pipvllm—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)
  • 0.8.5 up to 0.24.0: fixed in 0.24.0
  • every version through 0.23.0: no fix on record
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 9× in last 7d / 41× 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 233 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 133 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-01 16:34 UTCEPSS rescoreEPSS 0.4% · 39th percentile
  2. 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.4% · 39th percentile
  3. 2026-10-30 16:34 UTCEPSS rescoreEPSS 0.4% · 39th percentile
  4. 2026-10-29 16:33 UTCEPSS rescoreEPSS 0.4% · 39th percentile
  5. 2026-10-29 16:24 UTCEG score recompute
  6. 2026-10-29 16:24 UTCVendor advisory
  7. 2026-10-28 16:32 UTCEPSS rescoreEPSS 0.4% · 39th percentile
  8. 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  9. 2026-10-26 16:31 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  10. 2026-10-25 23:36 UTCEG score recompute
  11. 2026-10-25 23:36 UTCVendor advisory
  12. 2026-10-25 16:33 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  13. 2026-10-25 14:19 UTCEG score recompute
  14. 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  15. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  16. 2026-10-22 21:23 UTCEG score recompute
  17. 2026-10-22 16:34 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  18. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  19. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  20. 2026-10-19 16:32 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  21. 2026-10-18 16:32 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  22. 2026-10-18 03:31 UTCEG score recompute
  23. 2026-10-17 16:34 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  24. 2026-10-16 16:42 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  25. 2026-10-15 16:32 UTCEPSS rescoreEPSS 0.4% · 37th percentile
Show 75 more
  1. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  2. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  3. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  4. 2026-10-12 15:56 UTCEG score recompute
  5. 2026-10-11 19:39 UTCEG score recompute
  6. 2026-10-11 16:55 UTCEG score recompute
  7. 2026-10-11 14:18 UTCEG score recompute
  8. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  9. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  10. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  11. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  12. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  13. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  14. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  15. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  16. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  17. 2026-10-03 06:09 UTCOSV refresh
  18. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  19. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  20. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  21. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  22. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  23. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  24. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  25. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  26. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  27. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  28. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  29. 2026-09-17 19:31 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  30. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  31. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.4% · 38th percentile
  32. 2026-09-14 03:08 UTCEG score recompute
  33. 2026-09-14 03:08 UTCVendor advisory
  34. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  35. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  36. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  37. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  38. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  39. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  40. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  41. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  42. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  43. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  44. 2026-08-30 22:26 UTCEG score recompute
  45. 2026-08-30 22:26 UTCVendor advisory
  46. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  47. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  48. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  49. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  50. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  51. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.4% · 37th percentile
  52. 2026-08-24 06:59 UTCVendor advisory
  53. 2026-08-23 04:29 UTCEG score recompute
  54. 2026-08-23 04:29 UTCVendor advisory
  55. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  56. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  57. 2026-08-21 12:22 UTCEG score recompute
  58. 2026-08-21 12:22 UTCVendor advisory
  59. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  60. 2026-08-20 10:17 UTCEG score recompute
  61. 2026-08-20 10:17 UTCVendor advisory
  62. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  63. 2026-08-19 08:12 UTCEG score recompute
  64. 2026-08-19 08:12 UTCVendor advisory
  65. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  66. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  67. 2026-08-16 15:27 UTCEG score recompute
  68. 2026-08-16 15:27 UTCVendor advisory
  69. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  70. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  71. 2026-08-15 13:23 UTCEG score recompute
  72. 2026-08-15 13:23 UTCVendor advisory
  73. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  74. 2026-08-14 11:19 UTCEG score recompute
  75. 2026-08-14 11:19 UTCVendor advisory

Frequently asked(5)

What is CVE-2026-54235?
CVE-2026-54235 is a medium-severity vulnerability; its CVE record was published on June 17, 2026. vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and…
When was the CVE record for CVE-2026-54235 published?
The CVE record for CVE-2026-54235 was published on June 17, 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-2026-54235 actively exploited?
CVE-2026-54235 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (39th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-54235?
CVE-2026-54235 has a CVSS v3 base score of 6.5 (NVD).
How do I remediate CVE-2026-54235?
A fix for CVE-2026-54235 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-54235 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-2026-54235

Explore →

Is Your Infrastructure Affected by CVE-2026-54235?

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