Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-43630— llama.cpp b5702–b7653 Out-of-Bounds Read Information Disclosure

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.

ggml llama.cpp是ggml组织的一个在本地执行大语言模型推理的引擎。 ggml llama.cpp b5702至b7653版本和0.17.1版本存在安全漏洞，该漏洞源于循环内存状态恢复路径存在越界读取问题，可能导致攻击者通过制作带有超大seq_id值的恶意slot文件，触发越界读取，将堆数据（包括指针值）泄露到服务器日志中，绕过ASLR保护，便于进一步利用。

CVSS 6.5 · Medium EPSS 0.50% · P40

Affected Version Matrix 2

VendorProduct Version RangeStatus
ggml-org llama.cpp b5702≤ b7653 affected
0.17.1 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-43630

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 b5702–b7653 Out-of-Bounds Read Information Disclosure
Source: CVE Program / CVE List V5
Vulnerability Description
llama.cpp builds b5702 through b7653 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated cells array. Attackers can craft a malicious slot file with an oversized seq_id value to trigger an out-of-bounds read that leaks heap data including pointer values into server logs, defeating ASLR protections and facilitating further exploitation.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:L
Source: CVE Program / CVE List V5
Vulnerability Type
跨界内存读
Source: CVE Program / CVE List V5
Vulnerability Title
ggml llama.cpp 缓冲区错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
ggml llama.cpp是ggml组织的一个在本地执行大语言模型推理的引擎。 ggml llama.cpp b5702至b7653版本和0.17.1版本存在安全漏洞，该漏洞源于循环内存状态恢复路径存在越界读取问题，可能导致攻击者通过制作带有超大seq_id值的恶意slot文件，触发越界读取，将堆数据（包括指针值）泄露到服务器日志中，绕过ASLR保护，便于进一步利用。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
ggml-org llama.cpp b5702 ~ b7653 -

II. Public POCs for CVE-2026-43630

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-43630

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-43630 (2)

Vendor Pages for CVE-2026-43630 (1)

Other References for CVE-2026-43630 (1)

Same Patch Batch · ggml-org · 2026-08-06 · 10 CVEs total

CVE-2026-43632 8.1 HIGH llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
CVE-2026-43631 8.1 HIGH llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
CVE-2026-43629 8.1 HIGH llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
CVE-2026-43622 7.8 HIGH llama.cpp b1886–b7445 Double Free via llama-android.cpp
CVE-2026-43627 7.8 HIGH llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function
CVE-2026-43628 7.8 HIGH llama.cpp b3978–b9058 Integer Underflow via DRY Sampler
CVE-2026-70638 7.8 HIGH llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp
CVE-2026-70640 7.0 HIGH llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp
CVE-2026-70639 5.5 MEDIUM llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp

IV. Related Vulnerabilities

Same product: llama.cpp
Same vendor: ggml-org
Same weakness: CWE-125

V. Comments for CVE-2026-43630

No comments yet

Leave a comment