CVE-2026-94623

HIGHPre-NVD 7.57.5
EchelonGraph scoreMEDIUM confidence

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

Score 7.5 from GitHub Security Advisory (severity: HIGH) published 2026-09-22. A secondary CVSS source baseline 7.5; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, a secondary CVSS source

Also known asEUVD-2026-84217 (ENISA EUVD) · GHSA-g3cp-v4cp-9xfq (GitHub Security Advisories) · PYSEC-2026-4005 (OSV.dev)Source: ENISA EUVD

7.5EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines at low or medium mission impact and sooner than that at high (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 through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.

CVSS v3
7.5
EG Score
7.5HIGHmedium confidence
EG Risk
49
EG Risk 49/100

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.
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
0.6%
EPSS %ILE
50th
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 2026-11-05). 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

September 21, 2026

Last Modified

September 29, 2026

Advisory Details (4)

Auto-updated Sep 21, 2026
Patch available. Sources: github_pr.
Web page

vLLM through 0.29.0 Denial of Service via NIXL Multi-Prompt Assertion Failure | Advisories | VulnCheck

https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-nixl-multi-prompt-assertion-failure
GitHub pull request

fix: prevent NIXL Decode worker crash from multi-prompt completions

Upstream fix in progress (PR #51505 · vllm-project/vllm, state=open)

https://github.com/vllm-project/vllm/pull/51505
Web page

vllm/vllm/distributed/kv_transfer/kv_connector/v1/nixl/base_worker.py at v0.29.0 · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/base_worker.py#L2642-L2646
Web page

GitHub - vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMs · GitHub

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

Vendor Advisories for CVE-2026-94623(2)

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

Patch Availability(1)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhoai/odh-kserve-storage-initializer-rhel9:17909585492026-10-19redhat

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 (97 versions)
  • every version up to 0.30.0: fixed in 0.30.0
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 7× in last 7d / 39× 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 its CVE.org record (CNA or CISA ADP). 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). "EchelonGraph re-scored" is our own recompute of this CVE's score, not an update from a source, and is not counted in the refreshes above. Most recent first.

Showing the most recent 100 of 145 rows on record for this CVE, as 99 entries (1 repeat merged).

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. 1 repeat row among the latest 100 is merged into the row it repeats. The 45 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-13 16:58 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  2. 2026-11-12 16:35 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  3. 2026-11-11 16:41 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  4. 2026-11-10 16:46 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  5. 2026-11-09 16:36 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  6. 2026-11-08 16:41 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  7. 2026-11-07 16:40 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  8. 2026-11-06 16:40 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  9. 2026-11-06 03:11 UTCEchelonGraph re-scored
  10. 2026-11-06 03:11 UTCVendor advisory
  11. 2026-11-06 03:11 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  12. 2026-11-05 16:39 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  13. 2026-11-04 16:37 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  14. 2026-11-03 16:49 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  15. 2026-11-02 16:46 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  16. 2026-11-01 16:36 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  17. 2026-10-31 16:33 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  18. 2026-10-30 16:35 UTCEPSS rescoreEPSS 0.6% · 50th percentile
  19. 2026-10-29 16:34 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  20. 2026-10-29 14:15 UTCEchelonGraph re-scored
  21. 2026-10-29 14:15 UTCVendor advisory
  22. 2026-10-29 14:15 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  23. 2026-10-29 13:55 UTCOSV refresh
  24. 2026-10-28 16:33 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  25. 2026-10-27 16:33 UTCEPSS rescoreEPSS 0.6% · 49th percentile
Show 74 more
  1. 2026-10-26 16:33 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  2. 2026-10-25 16:34 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  3. 2026-10-25 13:49 UTCEchelonGraph re-scored
  4. 2026-10-24 16:34 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  5. 2026-10-23 16:33 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  6. 2026-10-22 16:35 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  7. 2026-10-22 00:33 UTCEchelonGraph re-scored
  8. 2026-10-22 00:33 UTCVendor advisory
  9. 2026-10-22 00:32 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  10. 2026-10-21 16:34 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  11. 2026-10-20 17:45 UTCEchelonGraph re-scored
  12. 2026-10-20 17:45 UTCVendor advisory
  13. 2026-10-20 17:45 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  14. 2026-10-20 16:34 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  15. 2026-10-19 16:33 UTCEPSS rescoreEPSS 0.6% · 49th percentile
  16. 2026-10-18 16:33 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  17. 2026-10-18 02:58 UTCEchelonGraph re-scored
  18. 2026-10-17 16:35 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  19. 2026-10-16 16:45 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  20. 2026-10-15 16:33 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  21. 2026-10-14 16:34 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  22. 2026-10-13 16:35 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  23. 2026-10-13 04:17 UTCEchelonGraph re-scored
  24. 2026-10-13 04:17 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  25. 2026-10-12 16:35 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  26. 2026-10-12 14:41 UTCEchelonGraph re-scored
  27. 2026-10-12 02:29 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  28. 2026-10-11 19:11 UTCEchelonGraph re-scored
  29. 2026-10-11 16:27 UTCEchelonGraph re-scored
  30. 2026-10-11 15:21 UTCEchelonGraph re-scored
  31. 2026-10-11 15:21 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  32. 2026-10-11 13:50 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  33. 2026-10-11 13:40 UTCEchelonGraph re-scored
  34. 2026-10-11 04:12 UTCEchelonGraph re-scored
  35. 2026-10-11 04:12 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  36. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  37. 2026-10-10 17:03 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  38. 2026-10-10 05:53 UTCEchelonGraph re-scored
  39. 2026-10-10 05:53 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  40. 2026-10-09 20:08 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  41. 2026-10-09 18:45 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  42. 2026-10-09 07:37 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  43. 2026-10-08 20:29 UTCEchelonGraph re-scored
  44. 2026-10-08 20:28 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  45. 2026-10-08 17:14 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  46. 2026-10-08 09:20 UTCEchelonGraph re-scored
  47. 2026-10-08 09:20 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  48. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  49. 2026-10-07 22:11 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  50. 2026-10-07 10:56 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  51. 2026-10-06 23:48 UTCEchelonGraph re-scored
  52. 2026-10-06 23:48 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  53. 2026-10-06 15:19 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  54. 2026-10-06 12:41 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  55. 2026-10-06 01:34 UTCEchelonGraph re-scored
  56. 2026-10-06 01:34 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  57. 2026-10-05 17:44 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  58. 2026-10-05 14:14 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  59. 2026-10-05 03:06 UTCEchelonGraph re-scored
  60. 2026-10-05 03:06 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  61. 2026-10-04 23:23 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  62. 2026-10-04 15:40 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  63. 2026-10-04 04:32 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  64. 2026-10-03 17:24 UTCEchelonGraph re-scored
  65. 2026-10-03 17:24 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  66. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  67. 2026-10-03 06:17 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  68. 2026-10-02 19:09 UTCEchelonGraph re-scored
  69. 2026-10-02 19:09 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  70. 2026-10-02 17:57 UTCEPSS rescoreEPSS 0.6% · 48th percentile
  71. 2026-10-02 08:01 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  72. 2026-10-01 20:54 UTCEchelonGraph re-scored
  73. 2026-10-01 20:53 UTCGHSA enrichmentGHSA-g3cp-v4cp-9xfq · GitHub severity HIGH · GitHub CVSS 7.5
  74. 2026-10-01 19:51 UTCEPSS rescoreEPSS 0.6% · 48th percentile

Frequently asked(5)

What is CVE-2026-94623?
CVE-2026-94623 is a high-severity vulnerability; its CVE record was published on September 21, 2026. vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in…
When was CVE-2026-94623 made public?
CVE-2026-94623 was made public on August 8, 2026: that is the date its CVE record's CNA, VulnCheck, gives for when the vulnerability was made public. The CVE record itself was published on September 21, 2026. EchelonGraph's copy of the record carries a last-modified date of September 29, 2026; the record at its source may have been updated since.
Is CVE-2026-94623 actively exploited?
CVE-2026-94623 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.6% probability of exploitation in the next 30 days (50th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-94623?
CVE-2026-94623 has a CVSS base score of 7.5 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-94623?
A fix for CVE-2026-94623 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-94623 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-2026-94623

Explore →

Is Your Infrastructure Affected by CVE-2026-94623?

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