CVE-2024-58399
llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
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.
Attack profile
How easy it is to exploit
- Attack vector
- Local
- Complexity
- Low
- Privileges needed
- None
- User interaction
- Passive
What an attacker can affect
- Confidentiality
- Low
- Integrity
- None
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
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.
- Record
CVE-2024-58399- CVSS 4.0
- 6.9 Medium
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N - CVSS 3.1
- 6.1 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H - Weakness
- CWE-125
- Updated
- 2026-11-02
EUVDEUVD-2024-55826
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.
- Record
EUVD-2024-55826- CVSS 4.0
- 6.9 Medium
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N - Updated
- 2026-11-03
GitHub AdvisoriesGHSA-xf8w-pfxh-7xj3
llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that...
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.
- Record
GHSA-xf8w-pfxh-7xj3- CVSS 4.0
- 6.9 Medium
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS 3.1
- 6.1 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H - Weakness
- CWE-125
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2024-58399- CVSS 4.0
- 6.9 Medium
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - CVSS 3.1
- 6.1 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H - Weakness
- CWE-125
- Updated
- 2026-11-03
OSV
llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
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.
- Record
CVE-2024-58399- CVSS 4.0
- 6.9 Medium
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N - Weakness
- CWE-125
- Updated
- 2026-11-04
OSVUBUNTU-CVE-2024-58399
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.
- Record
UBUNTU-CVE-2024-58399- CVSS 4.0
- 6.9 Medium
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N - CVSS 3.1
- 6.1 Medium
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H - Updated
- 2026-11-02
Affected products
Affected packages
History
| Recorded | Changed | Sources |
|---|---|---|
| facts | EUVD, NVD, OSV | |
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2024-58399 is a medium vulnerability (CVSS 6.9) in Ggml-org Llama.cpp, published October 27, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.12%, the 1st percentile. No source names a fixed version.
References
github.com/ggml-org/llama.cpp/issues/6774
vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets
Show 7 moreShow less
nvd.nist.gov/vuln/detail/CVE-2024-58399
ubuntu.com/security/CVE-2024-58399
cve.org/CVERecord?id=CVE-2024-58399