Critical severity · published Apr 1, 2026
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
9.8
CVSS
1.6%
EPSS
No
On KEV
Description
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)1.6% · higher than 76% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
< b8492 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-34159
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-34159
Patch
https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
Issue Tracking
https://github.com/ggml-org/llama.cpp/pull/20908
Exploit
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
More from llama.cpp
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
8.1
CVE-2026-43631
llama.cpp b7492–b9060 Use-After-Free RCE via llama-server