Skip to main content
VulnerabilityPublished Updated

CVE-2026-93436: vllm · Memory Leak

Affects vllmSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 8.7 High.

Data as of 1 Nov 2026, 22:58 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.7% chance of exploitation in 30 days – higher than 55% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 17 Sep 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 1 Nov 2026.

What to do

Affected software

ProductAffectedFixed in
vllm-projectvllmAffected
  • <=0.29.0
Fixed in–
GitHubvllm-project/vllmpkg:github/vllm-project/vllmOther threatsAffected
  • <=0.29.0
Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Until a fix is available, consider limiting or validating max_tokens parameters on incoming requests to mitigate memory exhaustion risk.

Description

vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens=0 to exhaust decode-worker memory without bound until the worker restarts.

References

Community reviews

Loading reviews…