CVE-2026-43632

high

Published 2026-08-06 · Modified 2026-08-06

Discuss on Community Propose mitigation

CVSS v3

8.1

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

CVSS v4 NEW

9.2

CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

VIR risk

8.1

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.

Predictions

Exploit likelihood

88%

Patch ETA

—

Heuristic predictions, AS-IS, for prioritization only.

Mitigations

No mitigations published for this CVE yet.

The vendor-content worker queues fetches as references arrive (check back in a few minutes). Or — if you've already worked around this in production — publish your fix to the community-verified tier.

Propose a mitigation on Community Mitigations published via the community go through AI scoring + 2 human reviewers + 7-day silent objection window before landing here with source_tier=community-verified.

References

https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches

CWEs

CWE-367 CWE-416

Community-verified mitigations for this CVE will appear above when contributors publish them.

Verify integrity in audit chain (admin only). AS-IS.