High severity · published Oct 28, 2026
CVE-2026-118375
llama.cpp b8841 before b11865 Stack-based Buffer Overflow via ggml-rpc RDMA rdma_recv()
New
8.1
CVSS
0.4%
EPSS
No
On KEV
Description
llama.cpp b8841 before b11865 contains an out-of-bounds write vulnerability in the ggml-rpc RDMA transport rdma_recv() function that allows unauthenticated peers to overflow the rpc-server stack. Attackers advertising RDMA capabilities in the HELLO message can send up to 256 KiB into a 1-byte stack variable in rpc_serve_client(), crashing the server or potentially executing code.
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)0.4% · higher than 31% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
b8841 before b11865 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-118375
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-118375
patch
https://github.com/ggml-org/llama.cpp/pull/30399
patch
https://github.com/ggml-org/llama.cpp/commit/9a0fde9967fa1a35b6e5dd1f47e1a3648b6fecc1
technical-description
https://github.com/ggml-org/llama.cpp/blob/620d2225cc436ab0b001e3200e590e3b286ef9ab/ggml/src/ggml-rpc/transport.cpp#L510-L528
release-notes
https://github.com/ggml-org/llama.cpp/releases/tag/b11865
product
https://github.com/ggml-org/llama.cpp
third-party-advisory
https://www.vulncheck.com/advisories/llama-cpp-b8841-before-b11865-stack-based-buffer-overflow-via-ggml-rpc-rdma-rdma-recv
More from llama.cpp
9.8
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
9.8
CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server
8.9
CVE-2025-53630
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
8.8
CVE-2025-52566
llama.cpp tokenizer signed vs. unsigned heap overflow
8.8
CVE-2025-49847
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model