CVE-2026-116829— llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader

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.

在版本 b11301 之前的 llama.cpp（具体为 b10398 及更早版本）中，函数存在一个整数溢出漏洞。该漏洞允许攻击者通过提供其维度乘积会回绕为零的张量形状，从而绕过张量元素数量验证。攻击者可构造包含超大张量维度的 GGUF 文件，导致和步长（strides）计算发生整数溢出；当缓冲区大小依据这些回绕后的字节数进行分配时，将引发越界内存访问。

CVSS 6.6 · Medium Updated Oct 27, 2026

Possible ATT&CK Techniques 2 AI

T1068 · Exploitation for Privilege Escalation T1203 · Exploitation for Client Execution

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 b10398 before b11301 Integer Overflow in gguf_init_from_reader

Source: CVE Program / CVE List V5

Vulnerability Description

llama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validation by supplying shapes whose product wraps to zero. Attackers can craft GGUF files with enormous tensor extents that overflow ggml_nbytes() and strides, causing out-of-bounds memory access when buffers are sized from wrapped byte counts.

Source: CVE Program / CVE List V5

CVSS Information

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

Source: CVE Program / CVE List V5

Vulnerability Type

整数溢出或超界折返

Source: CVE Program / CVE List V5

Affected Products

Vendor	Product	Affected Versions	CPE	Subscribe
ggml-org	llama.cpp	b10398 ~ b11301	-

II. Public POCs for CVE-2026-116829

#	POC Description	Source Link	Shenlong Link

AI-Generated POC Premium

No public POC found.

III. Intelligence Information for CVE-2026-116829

请登录查看更多情报信息。

Other References for CVE-2026-116829 (6)

https://github.com/ggml-org/llama.cpp/pull/29384 patch issue-tracking
https://github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f7ed9fc patch
https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L701 technical-description
https://github.com/ggml-org/llama.cpp/issues/29383 issue-tracking
https://github.com/ggml-org/llama.cpp/releases/tag/b11301 release-notes
https://www.vulncheck.com/advisories/llama-cpp-b10398-before-b11301-integer-overflow-in-gguf-init-from-reader third-party-advisory

https://www.cve.org/CVERecord?id=CVE-2026-116829

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-2026-116840	6.1 MEDIUM	llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader
CVE-2024-58399	6.1 MEDIUM	llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets
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-190