CVE-2026-33298

Published: Mar 24, 2026 Last Modified: Mar 24, 2026

ExploitDB:

Other exploit source:

Google Dorks:

HIGH 7,8

Source: [email protected]

Attack Vector: local

Attack Complexity: low

Privileges Required: none

User Interaction: required

Scope: unchanged

Confidentiality: high

Integrity: high

Availability: high

Description

AI Translation Available

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.

122

Heap-based Buffer Overflow

Draft

Abstraction: Variant Structure: Simple

Common Consequences

Security Scopes Affected:

Availability Integrity Confidentiality Access Control Other

Potential Impacts:

Dos: Crash, Exit, Or Restart Dos: Resource Consumption (Cpu) Dos: Resource Consumption (Memory) Execute Unauthorized Code Or Commands Bypass Protection Mechanism Modify Memory Other

Applicable Platforms

Languages: C, C++, Memory-Unsafe

Likelihood of Exploit: High

View CWE Details

190

Integer Overflow or Wraparound

Stable

Abstraction: Base Structure: Simple

Common Consequences

Security Scopes Affected:

Availability Integrity Confidentiality Access Control Other

Potential Impacts:

Dos: Crash, Exit, Or Restart Dos: Resource Consumption (Memory) Dos: Instability Modify Memory Execute Unauthorized Code Or Commands Bypass Protection Mechanism Alter Execution Logic Dos: Resource Consumption (Cpu)