CVE-2024-42479

10.0 CRITICAL

Published: August 12, 2024 Modified: April 27, 2026

Description

llama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This vulnerability is fixed in b3561.

AI Explanation

Get an AI-powered plain-language explanation of this vulnerability and remediation steps.

CVSS v3.x Details

0.0 Low Medium High Critical 10.0

Vector String

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

References to Advisories, Solutions, and Tools

Patch Vendor Advisory Exploit Third Party Advisory

https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b

Source: security-advisories@github.com

Patch

https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-wcr5-566p-9cwj

Source: security-advisories@github.com

Exploit Vendor Advisory

2 reference(s) from NVD

Quick Stats

CVSS v3 Score

10.0 / 10.0

EPSS (Exploit Probability)

5.7%

90th percentile

Exploitation Status

Not in CISA KEV

Weaknesses (CWE)

CWE-123 CWE-787

Affected Vendors

ggml

Related CVEs