High severity · published Mar 12, 2026
CVE-2026-27940
llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
7.8
CVSS
0.2%
EPSS
No
On KEV
Description
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack vector
Local
Complexity
Low
Privileges
None
User interaction
Required
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.2% · higher than 8% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
< b8146 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-27940
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-27940
Exploit
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v
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