8.6
HIGH
CVE-2025-52566
LLama Heap Overflow Vulnerability
Description

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.

INFO

Published Date :

June 24, 2025, 4:15 a.m.

Last Modified :

June 24, 2025, 10:15 p.m.

Remotely Exploitable :

No

Impact Score :

6.0

Exploitability Score :

1.8
Affected Products

The following products are affected by CVE-2025-52566 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

No affected product recoded yet

References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2025-52566.

URL Resource
https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2025-52566 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2025-52566 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Jun. 24, 2025

    Action Type Old Value New Value
    Added Reference https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
  • New CVE Received by [email protected]

    Jun. 24, 2025

    Action Type Old Value New Value
    Added Description llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
    Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
    Added CWE CWE-119
    Added CWE CWE-195
    Added Reference https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af
    Added Reference https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2025-52566 is associated with the following CWEs:

CVSS31 - Vulnerability Scoring System
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality
Integrity
Availability
© cvefeed.io
Latest DB Update: Jun. 25, 2025 14:24