CVE-2026-33298— llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
Get alerts for future matching vulnerabilitiesLog in to subscribe
I. Basic Information for CVE-2026-33298
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View Shenlong Deep Dive ↗ Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
Source: NVD (National Vulnerability Database)
Vulnerability Description
llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.
Source: NVD (National Vulnerability Database)
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Source: NVD (National Vulnerability Database)
Vulnerability Type
堆缓冲区溢出
Source: NVD (National Vulnerability Database)
Vulnerability Title
llama.cpp 输入验证错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
llama.cpp是Georgi Gerganov个人开发者的一个多模态模型。 llama.cpp b7824之前版本存在输入验证错误漏洞，该漏洞源于ggml_nbytes函数存在整数溢出，可能导致堆缓冲区溢出和远程代码执行。
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
II. Public POCs for CVE-2026-33298
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POCPremium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-33298
请登录查看更多情报信息。
Vendor · 1Advisory · 1
- Release b7824 · ggml-org/llama.cpp · GitHubx_refsource_MISC
- https://nvd.nist.gov/vuln/detail/CVE-2026-33298
IV. Related Vulnerabilities
Same product: llama.cpp
- CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 by - CVE-2026-27940
llama.cpp has a Heap Buffer Overflow via Integer Overflow in - CVE-2026-2069
ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_gram - CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server - CVE-2025-53630
Integer Overflow in GGUF Parser can lead to Heap Out-of-Boun
Same vendor: ggml-org
- CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 by - CVE-2026-27940
llama.cpp has a Heap Buffer Overflow via Integer Overflow in - CVE-2026-2069
ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_gram - CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server - CVE-2025-14569
ggml-org whisper.cpp common-whisper.cpp read_audio_data use
V. Comments for CVE-2026-33298
No comments yet