CVE-2026-43632
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
Description
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.
INFO
Published Date :
Aug. 6, 2026, 10:17 p.m.
Last Modified :
Aug. 8, 2026, 2:17 a.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | HIGH | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 3.1 | HIGH | MITRE-CVE | ||||
| CVSS 4.0 | CRITICAL | 83251b91-4cc7-4094-a5c7-464a1b83ea10 | ||||
| CVSS 4.0 | CRITICAL | [email protected] |
Solution
- Update llama.cpp to the latest version.
- Ensure proper synchronization for vocab access.
- Review and secure tokenization endpoint handling.
- Configure --sleep-idle-seconds carefully.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-43632.
| URL | Resource |
|---|---|
| https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches | |
| https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-43632 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-43632
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-43632 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-43632 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Aug. 08, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-43632', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-08-08T02:09:08.150856Z'} -
CVE Modified by [email protected]
Aug. 07, 2026
Action Type Old Value New Value Added Reference https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints -
New CVE Received by [email protected]
Aug. 06, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'ggml-org', 'product': 'llama.cpp', 'versions': [{'status': 'affected', 'version': 'b7492', 'versionType': 'custom', 'lessThanOrEqual': 'b9060'}], 'defaultStatus': 'affected'}] Added Description llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured. Added CVSS V4.0 AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/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 Added CVSS V3.1 AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H Added CWE CWE-416 Added CWE CWE-367 Added Reference https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches