CVE-2025-71439— llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info

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 b5649 版本之前的 llama.cpp 存在一个堆越界读取漏洞，该漏洞位于函数中。攻击者可通过提供过大的特殊令牌（special token）ID，导致模型加载过程崩溃。具体而言，攻击者可构造一个包含较短数组的 GGUF 模型，诱使或在读取映射表时越界访问，从而引发程序崩溃。

CVSS 5.5 · 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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info

Source: CVE Program / CVE List V5

Vulnerability Description

llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llama_vocab::impl::print_info() that allows attackers to crash model loading via oversized special token IDs. Attackers can supply a crafted GGUF model with a short tokenizer.ggml.tokens array, causing llama-cli or llama-server to read past id_to_token and crash.

Source: CVE Program / CVE List V5

CVSS Information

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/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	0 ~ b5649	-

II. Public POCs for CVE-2025-71439

#	POC Description	Source Link	Shenlong Link

AI-Generated POC Premium

No public POC found.

III. Intelligence Information for CVE-2025-71439

请登录查看更多情报信息。

Other References for CVE-2025-71439 (6)

https://github.com/ggml-org/llama.cpp/pull/14145 patch issue-tracking
https://github.com/ggml-org/llama.cpp/commit/c33fe8b8c4427202706b1434e9fc8ab5752c9cac patch
https://github.com/ggml-org/llama.cpp/blob/b5648/src/llama-vocab.cpp#L2771 technical-description
https://github.com/ggml-org/llama.cpp/releases/tag/b5649 release-notes
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-g4cc-763q-h9h6 vendor-advisory
https://www.vulncheck.com/advisories/llama-cpp-before-b5649-heap-out-of-bounds-read-via-llama-vocab-impl-print-info third-party-advisory

https://www.cve.org/CVERecord?id=CVE-2025-71439

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-2024-58399	6.1 MEDIUM	llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets

IV. Related Vulnerabilities

Same product: llama.cpp

Same vendor: ggml-org

Same weakness: CWE-125