CVEvulnerability
CVE-2026-43632
9.2 CRITICAL
Official page ↗
- Status
- Analyzed
- Published
- 2026-08-06
- Last modified
- 2026-10-23
- Assigner
- [email protected]
- CVSS 4.0 ([email protected])
- 9.2 CRITICAL — 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/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
- CVSS 3.1 ([email protected])
- 8.1 HIGH — CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
- Weaknesses
- CWE-367, CWE-416
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.
Affected configurations
• ggml llama.cpp (>= b7492 <= b9060)
Related
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches Patch, Third Party Advisory
- https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints Patch, Third Party Advisory