CVE-2026-43632Network attack vector

Remote code execution via tokenization use-after-free race

Published Aug 6, 2026 · Updated Aug 6, 2026

Use-after-free in llama-server builds b7492 through b9060 allows remote attackers to crash the service or execute code via tokenization requests. Six tokenization handlers bypass the task queue and access ctx_server.vocab on HTTP worker threads after the main thread can destroy it. Exploitation requires --sleep-idle-seconds and precise timing after lock release; successful races cause a service crash or code execution.

CVSS severity9.2
Critical
EPSS probability0.33%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Use-after-free in llama-server builds b7492 through b9060 allows remote attackers to crash the service or execute code via tokenization requests. Six tokenization handlers bypass the task queue and access ctx_server.vocab on HTTP worker threads after the main thread can destroy it. Exploitation requires --sleep-idle-seconds and precise timing after lock release; successful races cause a service crash or code execution.

The record

CVE
CVE-2026-43632
Published
Aug 6, 2026
Updated
Aug 6, 2026
Vendor
Georgi Gerganov
Product
llama.cpp
Classifications
CWE-367, CWE-416, T1190
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Aug 6, 2026CVE publishedPublication date reported by the CVE source.
  2. Aug 6, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=b7492 <=b9060

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Georgi Gerganov · llama.cppversion=b7492 <=b9060

Published CVSS scores

9.2VulnCheckCVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
8.1VulnCheckCVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-367Time-of-check Time-of-use (TOCTOU) Race Condition
CWE-416Use After Free
T1190Exploit Public-Facing Application

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo