High severity · published Aug 6, 2026
CVE-2026-43631
llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
8.1
CVSS
0.6%
EPSS
No
On KEV
Description
llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending requests to affected endpoints while the server transitions to sleep mode, causing concurrent worker threads to dereference a freed vocab pointer that can be reclaimed with attacker-controlled data to achieve remote code execution.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.6% · higher than 47% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
b7492 through b9060 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-43631
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-43631
Patch
https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
Patch
https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-rce-via-llama-server
More from llama.cpp
9.8
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
8.2
CVE-2024-58400
llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
8.1
CVE-2026-118375
llama.cpp b8841 before b11865 Stack-based Buffer Overflow via ggml-rpc RDMA rdma_recv()
8.1
CVE-2026-107183
llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser
8.1
CVE-2026-43632
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints