CVE-2026-7141

MEDIUMNVD 5.65.6
EchelonGraph scoreMEDIUM confidence

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

This medium-severity CVE scores 5.6 under NVD CVSS v3. EPSS exploit probability: 0.3% (21st 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 weekElevated

Also known asEUVD-2026-25892 (ENISA EUVD) · PYSEC-2026-2306 (OSV.dev)Source: ENISA EUVD

5.6EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • CISA's Vulnrichment rates exploitation as PoC; EchelonGraph holds no exploit-code reference for it
CISA-KEV: Not listedEPSS PROB: 0.3%CVSS: 5.6Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

A vulnerability was found in vLLM up to 0.19.0. The affected element is the function has_mamba_layers of the file vllm/v1/kv_cache_interface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is considered to have high complexity. The exploitability is described as difficult. The exploit has been made public and could be used. The existence of this vulnerability is still disputed at present. The proposed patch did not fix the issue. A 3rd party explains: "The divergence could be explained by a benign and expected vLLM behavior where vLLM server could group concurrent requests together resulting in different input shapes based on varying request arrival time. The differences in grouped input shapes could call different kernels with could produce difference results due to rounding and differences in order of operations. There is an environment variable VLLM_BATCH_INVARIANT=1 for users that desire to have deterministic output with temperature 0.0."

CVSS v3
5.6
EG Score
5.6MEDIUMmedium confidence
EG Risk
41
EG Risk 41/100

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)
Severity56% × 45%
Impact severity (EG Severity): CVSS 5.6 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
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 public PoC (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
0.3%
EPSS %ILE
21st
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 (5.6): severity, escalated by confirmed exploitation. This CVE's 5.6 is its impact severity (EG Severity), not escalated.

EG Severity
5.6 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
0.3% within 30 daysSource: FIRST EPSS. 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; Track* at high (mission-essential systems).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: the SSVC and BOD 26-04 blocks below.

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 public PoC (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.

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

April 27, 2026

Last Modified

August 25, 2026

Advisory Details (4)

Auto-updated May 1, 2026
Patch available.
Web page

[Bugfix] Zero recycled KV cache blocks for FullAttention models by AjAnubolu · Pull Request #39283 · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/pull/39283
Web page

[Bug]: KV block corruption in base scheduler, Non-deterministic output at temperature=0 without prefix caching · Issue #39146 · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/issues/39146#issue-4215090365
Web page

[Bug]: KV block corruption in base scheduler, Non-deterministic output at temperature=0 without prefix caching · Issue #39146 · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/issues/39146
Web page

Zero recycled KV blocks for FullAttention models (#39146) · AjAnubolu/vllm@1ad6786 · GitHub

https://github.com/AjAnubolu/vllm/commit/1ad67864c0c20f167929e64c875f5c28e1aad9fd

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
vllm0.0.1 ... 0.9.2 (81 versions)
  • every version up to 0.19.1: fixed in 0.19.1
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 9× in last 7d / 38× 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 93 of 187 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. 7 repeat rows among the latest 100 are merged into the row they repeat. The 94 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-30 07:25 UTCOSV refresh
  2. 2026-10-29 16:34 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  3. 2026-10-28 16:33 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  4. 2026-10-27 16:32 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  5. 2026-10-26 16:32 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  6. 2026-10-25 16:34 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  7. 2026-10-25 14:07 UTCEG score recompute
  8. 2026-10-24 16:33 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  9. 2026-10-23 16:32 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  10. 2026-10-22 19:24 UTCEG score recompute
  11. 2026-10-22 16:35 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  12. 2026-10-21 16:33 UTCEPSS rescoreEPSS 0.5% · 40th percentile
  13. 2026-10-20 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  14. 2026-10-19 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  15. 2026-10-18 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  16. 2026-10-18 03:17 UTCEG score recompute
  17. 2026-10-17 16:35 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  18. 2026-10-16 16:44 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  19. 2026-10-15 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  20. 2026-10-14 16:33 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  21. 2026-10-13 16:35 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  22. 2026-10-12 16:35 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  23. 2026-10-12 15:42 UTCEG score recompute
  24. 2026-10-11 19:28 UTCEG score recompute
  25. 2026-10-11 16:43 UTCEG score recompute
Show 68 more
  1. 2026-10-11 14:04 UTCEG score recompute
  2. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  3. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  4. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  5. 2026-10-08 17:13 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  6. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  7. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  8. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  9. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  10. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  11. 2026-10-02 21:40 UTCOSV refresh
  12. 2026-10-02 17:57 UTCEPSS rescoreEPSS 0.5% · 39th percentile
  13. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  14. 2026-09-29 15:24 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  15. 2026-09-28 13:52 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  16. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  17. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  18. 2026-09-26 00:28 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  19. 2026-09-24 14:04 UTCEPSS rescoreEPSS 0.5% · 38th percentile
  20. 2026-09-23 17:54 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  21. 2026-09-22 16:01 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  22. 2026-09-21 21:09 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  23. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  24. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  25. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  26. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  27. 2026-09-15 03:12 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  28. 2026-09-13 19:09 UTCOSV refresh
  29. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  30. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  31. 2026-09-06 13:48 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  32. 2026-09-04 05:07 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  33. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  34. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  35. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  36. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  37. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  38. 2026-08-28 21:42 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  39. 2026-08-26 14:47 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  40. 2026-08-25 20:23 UTCNVD updateCVSS v4 → 2.9
  41. 2026-08-25 19:25 UTCEG score recompute
  42. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  43. 2026-08-24 14:18 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  44. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  45. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  46. 2026-08-20 22:56 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  47. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  48. 2026-08-18 13:49 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  49. 2026-08-17 14:02 UTCEG score recompute
  50. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  51. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  52. 2026-08-16 05:37 UTCEG score recompute
  53. 2026-08-16 02:15 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  54. 2026-08-15 01:31 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  55. 2026-08-14 04:01 UTCEG score recompute
  56. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  57. 2026-08-12 17:41 UTCEG score recompute
  58. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  59. 2026-08-11 06:32 UTCEG score recompute
  60. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  61. 2026-08-10 04:51 UTCEG score recompute
  62. 2026-08-09 13:47 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  63. 2026-08-09 03:11 UTCEG score recompute
  64. 2026-08-07 12:23 UTCEG score recompute
  65. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  66. 2026-08-05 22:49 UTCEG score recompute
  67. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  68. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.3% · 21st percentile

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-7141?
CVE-2026-7141 is a medium-severity vulnerability; its CVE record was published on April 27, 2026. A vulnerability was found in vLLM up to 0.19.0. The affected element is the function hasmambalayers of the file vllm/v1/kvcacheinterface.py of the component KV Block Handler. Performing a manipulation results in uninitialized resource. It is possible to initiate the attack remotely. The attack is…
When was the CVE record for CVE-2026-7141 published?
The CVE record for CVE-2026-7141 was published on April 27, 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 August 25, 2026; the record at its source may have been updated since.
Is CVE-2026-7141 actively exploited?
CVE-2026-7141 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.3% probability of exploitation in the next 30 days (21st percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-7141?
CVE-2026-7141 has a CVSS v3 base score of 5.6 (NVD).
How do I remediate CVE-2026-7141?
A fix for CVE-2026-7141 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-2026-7141

Explore →

Is Your Infrastructure Affected by CVE-2026-7141?

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

Book a Demo →Browse All CVEs