CVE-2026-100651

MEDIUMPre-NVD 6.56.5—
EchelonGraph scoreHIGH confidence

Score 6.5 from GitHub Security Advisory (severity: HIGH) published 2026-09-26. A secondary CVSS source baseline 6.5; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: epss, ghsa, secondary
Trending — 3 sources updated this weekElevated
6.5EG
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.3%CVSS: 6.5Exploit: Elevated riskExposed services: Not assessed

A fix is available — apply it.

vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0.

CVSS v3
6.5
EG Score
6.5MEDIUMhigh confidence
EG Risk
45
EG Risk 45/100CISA SSVC

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
Severity65% × 45%
Exploitation40% × 40%
Automatability0% × 15%
CISA SSVC: Track at low or medium mission impact; Track* at high (mission-essential systems).
Action: A fix is available. Apply it within your standard update timelines.
EPSS PROB
0.3%
EPSS %ILE
21st
KEV
Not listed

CISA SSVCTrack 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). Mission impact is CISA's Mission & Well-being decision point, and only you can judge it: high means the affected system is essential to your organisation's mission, or its compromise could cause irreversible harm to people. CISA's decision table

Published

September 26, 2026

Last Modified

September 28, 2026

Advisory Details (2)

Auto-updated Sep 26, 2026
Patch available. Sources: github.
generic

vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass | Advisories | VulnCheck

https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-decoder-prompt-length-bypass
github Patch Available

Disaggregated generate skips decoder prompt-length validation for some multimodal processors · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9

Vendor Advisories for CVE-2026-100651(1)

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

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 25× in last 7d / 30× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. 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. Most recent first.

  1. 2026-10-05 04:27 UTCEG score recompute
  2. 2026-10-05 04:27 UTCGHSA enrichment
  3. 2026-10-04 23:21 UTCEPSS rescore
  4. 2026-10-04 03:31 UTCEG score recompute
  5. 2026-10-04 03:31 UTCGHSA enrichment
  6. 2026-10-03 14:25 UTCEPSS rescore
  7. 2026-10-03 02:36 UTCEG score recompute
  8. 2026-10-03 02:36 UTCGHSA enrichment
  9. 2026-10-02 01:40 UTCEG score recompute
  10. 2026-10-02 01:40 UTCGHSA enrichment
  11. 2026-10-01 19:49 UTCEPSS rescore
  12. 2026-10-01 00:42 UTCEG score recompute
  13. 2026-10-01 00:42 UTCGHSA enrichment
  14. 2026-09-30 15:02 UTCEPSS rescore
  15. 2026-09-29 23:48 UTCEG score recompute
  16. 2026-09-29 23:48 UTCGHSA enrichment
  17. 2026-09-29 15:20 UTCEPSS rescore
  18. 2026-09-28 21:13 UTCGHSA enrichment
  19. 2026-09-28 19:30 UTCEG score recompute
  20. 2026-09-28 19:29 UTCGHSA enrichment
  21. 2026-09-28 18:37 UTCEG score recompute
  22. 2026-09-28 18:37 UTCGHSA enrichment
  23. 2026-09-28 16:27 UTCEG score recompute
  24. 2026-09-28 16:27 UTCGHSA enrichment
  25. 2026-09-28 13:50 UTCEPSS rescore
Show 5 more
  1. 2026-09-27 15:32 UTCEG score recompute
  2. 2026-09-27 15:31 UTCGHSA enrichment
  3. 2026-09-26 14:34 UTCEG score recompute
  4. 2026-09-26 13:38 UTCEG score recompute
  5. 2026-09-26 13:30 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-100651?
CVE-2026-100651 is a medium vulnerability published on September 26, 2026. vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied…
When was CVE-2026-100651 disclosed?
CVE-2026-100651 was first published on September 26, 2026, with the most recent update on September 28, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-100651 actively exploited?
CVE-2026-100651 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-2026-100651?
CVE-2026-100651 has a CVSS base score of 6.5 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-100651?
A fix for CVE-2026-100651 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-100651 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-100651

Explore →

Is Your Infrastructure Affected by CVE-2026-100651?

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

Book a Demo →Browse All CVEs