CVE-2026-100650

MEDIUMPre-NVD 6.56.5
EchelonGraph scoreMEDIUM confidence

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

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, GitHub Security Advisory, a secondary CVSS source
Trending — 4 sources updated this weekElevated

Also known asEUVD-2026-87744 (ENISA EUVD) · GHSA-j8gm-f3cq-6c27 (GitHub Security Advisories)Source: ENISA EUVD

6.5EG
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: 0.8%CVSS: 6.5Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.

CVSS v3
6.5
EG Score
6.5MEDIUMmedium confidence
EG Risk
45
EG Risk 45/100

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)
Severity65% × 45%
Impact severity (EG Severity): CVSS 6.5 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
0.8%
EPSS %ILE
56th
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 (6.5): severity, escalated by confirmed exploitation. This CVE's 6.5 is its impact severity (EG Severity), not escalated.

EG Severity
6.5 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
EG Likelihood
0.8% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-25). 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, 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; 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.

The score's inputs: 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

September 26, 2026

Last Modified

October 6, 2026

Advisory Details (3)

Auto-updated Sep 26, 2026
Patch available. Sources: github, github_commit.
Web page

vLLM before 0.29.0 Resource Exhaustion via Unbounded Media Materialization | Advisories | VulnCheck

https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization
GitHub commit

commit 752a3a504485 (vllm-project/vllm)

Fix landed in vllm-project/vllm commit 752a3a504485 — awaiting tagged release

https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34
GitHub advisoryMentions a patch (unverified)

Remote media is fetched and fully materialized before the documented media size / item limits are enforced — remote pre-inference memory and bandwidth exhaustion (4 sites) · Advisory · vllm-project/vllm · GitHub

https://github.com/vllm-project/vllm/security/advisories/GHSA-p6g9-7v3x-m8mv

Patch Availability(5)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
redhatrhoai/odh-kserve-storage-initializer-rhel9:17909585492026-10-19redhat
redhatrhaii/vllm-rocm-rhel9:17918567252026-10-14redhat
redhatrhaii/vllm-cpu-rhel9:17918573012026-10-14redhat
redhatrhaii/vllm-spyre-rhel9:17918585922026-10-14redhat
redhatrhaii/vllm-cuda-rhel9:17918571832026-10-14redhat

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 10× in last 7d / 60× 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. 2026-11-01 16:33 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  2. 2026-10-31 16:31 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  3. 2026-10-30 16:33 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  4. 2026-10-29 16:32 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  5. 2026-10-28 16:31 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  6. 2026-10-27 16:31 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  7. 2026-10-26 16:30 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  8. 2026-10-26 15:32 UTCEG score recompute
  9. 2026-10-26 15:32 UTCVendor advisory
  10. 2026-10-26 15:32 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  11. 2026-10-25 16:32 UTCEPSS rescoreEPSS 0.8% · 56th percentile
  12. 2026-10-25 15:58 UTCEG score recompute
  13. 2026-10-24 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  14. 2026-10-23 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  15. 2026-10-23 09:53 UTCEG score recompute
  16. 2026-10-23 09:53 UTCVendor advisory
  17. 2026-10-23 09:53 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  18. 2026-10-22 16:33 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  19. 2026-10-21 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  20. 2026-10-20 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  21. 2026-10-19 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  22. 2026-10-18 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  23. 2026-10-18 05:11 UTCEG score recompute
  24. 2026-10-17 16:33 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  25. 2026-10-16 16:40 UTCEPSS rescoreEPSS 0.7% · 50th percentile
Show 57 more
  1. 2026-10-15 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  2. 2026-10-14 16:31 UTCEPSS rescoreEPSS 0.7% · 50th percentile
  3. 2026-10-13 16:33 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  4. 2026-10-12 16:41 UTCEG score recompute
  5. 2026-10-12 16:33 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  6. 2026-10-12 04:22 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  7. 2026-10-11 20:16 UTCEG score recompute
  8. 2026-10-11 18:29 UTCEG score recompute
  9. 2026-10-11 15:02 UTCEG score recompute
  10. 2026-10-11 13:47 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  11. 2026-10-11 02:37 UTCEG score recompute
  12. 2026-10-11 02:37 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  13. 2026-10-10 19:59 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  14. 2026-10-10 00:53 UTCEG score recompute
  15. 2026-10-10 00:53 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  16. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  17. 2026-10-08 23:23 UTCEG score recompute
  18. 2026-10-08 23:22 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  19. 2026-10-08 17:11 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  20. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.7% · 49th percentile
  21. 2026-10-07 21:51 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  22. 2026-10-06 19:54 UTCEG score recompute
  23. 2026-10-06 19:54 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  24. 2026-10-06 18:51 UTCEG score recompute
  25. 2026-10-06 18:51 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  26. 2026-10-06 15:17 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  27. 2026-10-05 17:42 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  28. 2026-10-05 17:22 UTCEG score recompute
  29. 2026-10-05 17:21 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  30. 2026-10-04 23:21 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  31. 2026-10-04 15:52 UTCEG score recompute
  32. 2026-10-04 15:51 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  33. 2026-10-03 14:25 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  34. 2026-10-03 14:20 UTCEG score recompute
  35. 2026-10-03 14:20 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  36. 2026-10-02 12:50 UTCEG score recompute
  37. 2026-10-02 12:50 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  38. 2026-10-01 19:49 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  39. 2026-10-01 11:21 UTCEG score recompute
  40. 2026-10-01 11:21 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  41. 2026-09-30 15:39 UTCEG score recompute
  42. 2026-09-30 15:39 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  43. 2026-09-30 15:02 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  44. 2026-09-30 14:53 UTCEG score recompute
  45. 2026-09-30 14:53 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  46. 2026-09-29 23:48 UTCEG score recompute
  47. 2026-09-29 23:48 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  48. 2026-09-29 15:20 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  49. 2026-09-28 20:50 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  50. 2026-09-28 17:46 UTCEG score recompute
  51. 2026-09-28 17:46 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  52. 2026-09-28 13:50 UTCEPSS rescoreEPSS 0.6% · 47th percentile
  53. 2026-09-27 16:04 UTCEG score recompute
  54. 2026-09-27 16:04 UTCGHSA enrichmentGHSA-j8gm-f3cq-6c27 · GitHub severity HIGH · GitHub CVSS 6.5
  55. 2026-09-26 14:34 UTCEG score recompute
  56. 2026-09-26 13:38 UTCEG score recomputeFirst assessed: 6.5 MEDIUM
  57. 2026-09-26 13:30 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-100650?
CVE-2026-100650 is a medium-severity vulnerability; its CVE record was published on September 26, 2026. vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared…
When was CVE-2026-100650 made public?
CVE-2026-100650 was made public on September 12, 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 26, 2026. EchelonGraph's copy of the record carries a last-modified date of October 6, 2026; the record at its source may have been updated since.
Is CVE-2026-100650 actively exploited?
CVE-2026-100650 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.8% probability of exploitation in the next 30 days (56th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-100650?
CVE-2026-100650 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-2026-100650?
A fix for CVE-2026-100650 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-100650 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-2026-100650

Explore →

Is Your Infrastructure Affected by CVE-2026-100650?

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