CVE-2026-105760

MEDIUMPre-NVD 5.35.3
EchelonGraph scoreHIGH confidence

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

Score 5.3 from GitHub Security Advisory (severity: MODERATE) published 2026-10-05. A secondary CVSS source baseline 5.3; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, a secondary CVSS source
Trending — 4 sources updated this week

Also known asEUVD-2026-92851 (ENISA EUVD) · GHSA-58v5-2m8f-94pr (GitHub Security Advisories) · PYSEC-2026-4307 (OSV.dev)Source: ENISA EUVD

5.3EG
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: 0.3%CVSS: 5.3Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.

CVSS v3
5.3
EG Score
5.3MEDIUMhigh confidence
EG Risk
39
EG Risk 39/100

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)
Severity53% × 45%
Impact severity (EG Severity): CVSS 5.3 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation0.3% × 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
0.3%
EPSS %ILE
22nd
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 (5.3): severity, escalated by confirmed exploitation. This CVE's 5.3 is its impact severity (EG Severity), not escalated.

EG Severity
5.3 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
0.3% 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 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

October 5, 2026

Last Modified

October 16, 2026

Advisory Details (4)

Auto-updated Oct 5, 2026
Patch available. Sources: github_commit, github_pr, github_release, github.
GitHub advisoryMentions a patch (unverified)

GLMGA video sampling permits request-driven CPU and memory exhaustion · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-58v5-2m8f-94pr
GitHub release Patch Available

v0.30.0

Patch available: vllm-project/vllm v0.30.0

https://github.com/vllm-project/vllm/releases/tag/v0.30.0
GitHub pull request

[Security] Cap GLMGA video sampling to prevent request-driven resource exhaustion

Fix merged in vllm-project/vllm PR #54935 on 2026-09-04 — awaiting tagged release

https://github.com/vllm-project/vllm/pull/54935
GitHub commit

commit 8b6de0eb9a09 (vllm-project/vllm)

Fix landed in vllm-project/vllm commit 8b6de0eb9a09 — awaiting tagged release

https://github.com/vllm-project/vllm/commit/8b6de0eb9a09ef53f20cf06bd4d17ee264b9c2a7

Vendor Advisories for CVE-2026-105760(1)

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
pipvllm @ 0.30.0 (fixes >= 0.23.0rc2, < 0.30.0)—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
vllm0.23.0 ... 0.29.0 (9 versions)
  • 0.23.0rc2 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 10× in last 7d / 46× 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.

  1. 2026-11-02 16:43 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  2. 2026-11-01 16:33 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  3. 2026-11-01 08:00 UTCEG score recompute
  4. 2026-11-01 08:00 UTCGHSA enrichmentGHSA-58v5-2m8f-94pr · GitHub severity MODERATE · GitHub CVSS 5.3
  5. 2026-10-31 16:31 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  6. 2026-10-30 16:33 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  7. 2026-10-29 16:32 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  8. 2026-10-28 16:31 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  9. 2026-10-28 02:55 UTCOSV refresh
  10. 2026-10-27 16:31 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  11. 2026-10-26 16:30 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  12. 2026-10-25 16:32 UTCEPSS rescoreEPSS 0.3% · 22nd percentile
  13. 2026-10-25 14:55 UTCEG score recompute
  14. 2026-10-24 16:32 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  15. 2026-10-23 16:31 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  16. 2026-10-22 16:33 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  17. 2026-10-21 16:32 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  18. 2026-10-20 16:31 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  19. 2026-10-19 16:31 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  20. 2026-10-18 16:31 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  21. 2026-10-18 05:08 UTCEG score recompute
  22. 2026-10-17 16:33 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  23. 2026-10-16 20:59 UTCEG score recompute
  24. 2026-10-16 16:40 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  25. 2026-10-15 16:31 UTCEPSS rescoreEPSS 0.3% · 21st percentile
Show 21 more
  1. 2026-10-14 16:31 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  2. 2026-10-13 16:33 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  3. 2026-10-12 16:39 UTCEG score recompute
  4. 2026-10-12 16:33 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  5. 2026-10-11 20:15 UTCEG score recompute
  6. 2026-10-11 18:27 UTCEG score recompute
  7. 2026-10-11 15:01 UTCEG score recompute
  8. 2026-10-11 13:47 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  9. 2026-10-11 00:54 UTCEG score recompute
  10. 2026-10-10 19:59 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  11. 2026-10-09 22:29 UTCEG score recompute
  12. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.3% · 21st percentile
  13. 2026-10-08 20:06 UTCEG score recompute
  14. 2026-10-08 17:11 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  15. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  16. 2026-10-06 15:22 UTCEG score recompute
  17. 2026-10-06 15:17 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  18. 2026-10-06 14:55 UTCEG score recompute
  19. 2026-10-05 23:26 UTCEG score recompute
  20. 2026-10-05 23:08 UTCEG score recomputeFirst assessed: 5.3 MEDIUM
  21. 2026-10-05 23:05 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-105760?
CVE-2026-105760 is a medium-severity vulnerability; its CVE record was published on October 5, 2026. vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates…
When was the CVE record for CVE-2026-105760 published?
The CVE record for CVE-2026-105760 was published on October 5, 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 16, 2026; the record at its source may have been updated since.
Is CVE-2026-105760 actively exploited?
CVE-2026-105760 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.3% probability of exploitation in the next 30 days (22nd percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-105760?
CVE-2026-105760 has a CVSS base score of 5.3 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-105760?
A fix for CVE-2026-105760 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-105760 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-2026-105760

Explore →

Is Your Infrastructure Affected by CVE-2026-105760?

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