CVE-2026-54232

HIGHPre-NVD 8.88.8
EchelonGraph scoreMEDIUM confidence

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

This high-severity CVE scores 8.8 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.6% (45th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from a secondary CVSS source
Sources: EPSS, a secondary CVSS source
Trending — 3 sources updated this week
8.8EG
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: 8.8Exploit: 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 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.

CVSS v3
8.8
EG Score
8.8HIGHmedium confidence
EG Risk
40
EG Risk 40/100

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed (value × EchelonGraph’s weight)
Severity88% × 45%
The EG Score, 8.8 of 10.
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 low or medium mission impact; Track* at high (mission-essential systems).
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (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
45th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Track* at high (mission-essential systems).

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

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (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; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact total (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 22, 2026

Last Modified

June 24, 2026

Advisory Details (1)

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

Dependency Confusion Vulnerability in vLLM Dockerfile · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
vllm0.0.1 ... 0.9.2 (87 versions)
  • every version up to 0.22.1: fixed in 0.22.1
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 12× in last 7d / 31× 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 152 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 52 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

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

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-54232?
CVE-2026-54232 is a high-severity vulnerability; its CVE record was published on June 22, 2026. vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the…
When was the CVE record for CVE-2026-54232 published?
The CVE record for CVE-2026-54232 was published on June 22, 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 June 24, 2026; the record at its source may have been updated since.
Is CVE-2026-54232 actively exploited?
CVE-2026-54232 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.6% probability of exploitation in the next 30 days (45th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-54232?
CVE-2026-54232 has a CVSS base score of 8.8 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-54232?
A fix for CVE-2026-54232 is available: update to the fixed version the vendor names in its advisory.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-54232

Explore →

Is Your Infrastructure Affected by CVE-2026-54232?

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

Book a Demo →Browse All CVEs