Login Request a demo
Medium severity · published Oct 27, 2026
CVE-2024-58399
llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
New
6.1
CVSS
0.1%
EPSS
No
On KEV
Description
llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
Attack vector
Local
Complexity
Low
Privileges
None
User interaction
Required
Confidentiality
Low
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.1% · higher than 2% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
b1046 before b2731 · source: vendor
Affected product
LL
llama.cpp
ggml-org
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2024-58399
CVE.org
https://www.cve.org/CVERecord?id=CVE-2024-58399
github.com
https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004
github.com
https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d
github.com
https://github.com/ggml-org/llama.cpp/issues/6774
github.com
https://github.com/ggml-org/llama.cpp/pull/6885
github.com
https://github.com/ggml-org/llama.cpp/releases/tag/b2731
www.vulncheck.com
https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets
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