Skip to main content
No exploitation reportedFix available

CVE-2026-100647

No exploitation reported by the sources we read.

  • Published2026-09-26
  • Fixed in0.29.0
  • WeaknessCWE-20

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

Description

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.

Timeline

dates in UTC
  1. 2026-09-2614:16CVE publishedNVD

Observed activity

isMalicious corpus · updated 2026-10-23 18:48 UTC
Indicators tagged with this CVE, per day0 indicators over 7 days
Block these indicators
  • Firewall list (EDL, text): https://api.ismalicious.com/edl/cve/CVE-2026-100647?format=txt
  • CSV export: https://api.ismalicious.com/edl/cve/CVE-2026-100647?format=csv
  • TAXII collection of exploited CVEs
  • The EDL and CSV take an API key on the Pro plan.

Versions per branch

NVD
Vllm
BranchAffectedFixed in
0.29< 0.29.00.29.0

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Distribution builds and vendor advisories

Packages from OSV.dev and products from the vendors' CSAF advisories.

version not verifiedVersions not verified: read as OSV.dev and the vendors publish them, not checked against each vendor's release list.

Vendor advisories

  • CVE-2026-100647 Red Hat Product Security27 known affected

    vllm: vLLM: Denial of Service via unbounded cache_salt parameter

    rhaii/vllm-cpu-rhel9 as a component of Red Hat AI Inference Server · rhaii/vllm-cuda-rhel9 as a component of Red Hat AI Inference Server · rhaii/vllm-gaudi-rhel9 as a component of Red Hat AI Inference Server · +24 more

Full record on NVD

Fix

  1. Update Vllm to 0.29.0
  2. Workaround from the vendor Red Hat Product Security CVE-2026-100647 · 27 productsThere is no vLLM env-var toggle that bounds cache_salt on vulnerable builds. Try to strip or deny cache_salt at the gateway or put Auth + rate limits on OpenAI/Anthropic-compatible endpoints.
  3. No fix available, says the vendor Red Hat Product Security CVE-2026-100647 · 27 productsFix deferred

Advisories and patches

Detection

Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof-of-concept repositories
none listed
PoC-in-GitHub

Sources

  • CISA-ADPSSVC decisionnone2026-09-28
  • OpenCVESSVC decisionnone—
  • CNACVSS 4.06.9read 2026-10-23
  • CNACVSS 3.15.3read 2026-10-23
  • NVDCVSS 3.17.5read 2026-10-23
  • CNAweakness (CWE)CWE-20read 2026-10-23
  • FIRST EPSSEPSS score0.3 %2026-10-22

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
CVSS 4.0 vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Published
2026-09-26
Last Modified
2026-10-06
NVD status
Analyzed

Frequently asked questions

What is CVE-2026-100647?

vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, which lacks maximum length validation and is processed on the single EngineCore scheduler thread. Unauthenticated attackers can send HTTP requests with multi-hundred-megabyte salt values that trigger expensive pickle serialization and SHA-256 hashing, stalling the scheduler thread and denying service to all concurrent requests.

Is CVE-2026-100647 actively exploited?

Active exploitation of CVE-2026-100647 has not been confirmed. Its EPSS score was 0.3% on 2026-10-22, the estimated probability of exploitation in the next 30 days.

What is the CVSS score for CVE-2026-100647?

CVE-2026-100647 has a CVSS v3 base score of 7.5 (HIGH severity), with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.

Running vllm? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

No credit card required · No monthly cap on website lookups · 250 API requests/month