CVE-2024-58399— llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

Quick assessment

Affected

ggml-org llama.cpp

Exploitation

No confirmed in-the-wild exploitation; assess based on exposure

Recommended action

Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

在 b2731 版本之前的 llama.cpp 中，llama_model_loader 组件存在一个越界读取漏洞。攻击者可通过构造恶意的 GGUF 张量偏移量，读取映射模型文件之外的内存。攻击者可以提供一个经过篡改或截断的 GGUF 模型文件，其中包含任意的 64 位张量偏移量，从而导致进程崩溃，或将相邻进程的内存作为模型权重加载。

CVSS 6.1 · Medium Updated Oct 27, 2026

Possible ATT&CK Techniques 1 AI

T1190 · Exploit Public-Facing Application

Get alerts for future matching vulnerabilities Log in to subscribe

Vulnerability Information

Have questions about the vulnerability? See if Shenlong's analysis helps!

View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title

llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

Source: CVE Program / CVE List V5

Vulnerability 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.

Source: CVE Program / CVE List V5

CVSS Information

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H

Source: CVE Program / CVE List V5

Vulnerability Type

跨界内存读

Source: CVE Program / CVE List V5

Affected Products

Vendor	Product	Affected Versions	CPE	Subscribe
ggml-org	llama.cpp	b1046 ~ b2731	-

II. Public POCs for CVE-2024-58399

#	POC Description	Source Link	Shenlong Link

AI-Generated POC Premium

No public POC found.

III. Intelligence Information for CVE-2024-58399

请登录查看更多情报信息。

Other References for CVE-2024-58399 (6)

https://github.com/ggml-org/llama.cpp/pull/6885 patch issue-tracking
https://github.com/ggml-org/llama.cpp/issues/6774 issue-tracking
https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004 technical-description
https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d patch
https://github.com/ggml-org/llama.cpp/releases/tag/b2731 release-notes
https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets third-party-advisory

https://www.cve.org/CVERecord?id=CVE-2024-58399

Same Patch Batch · ggml-org · 2026-10-27 · 6 CVEs total

CVE-2024-58400	8.2 HIGH	llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs
CVE-2026-116816	7.8 HIGH	llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer
CVE-2026-116829	6.6 MEDIUM	llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
CVE-2026-116840	6.1 MEDIUM	llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader
CVE-2025-71439	5.5 MEDIUM	llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info

IV. Related Vulnerabilities

Same product: llama.cpp

Same vendor: ggml-org

Same weakness: CWE-125