9.8
CRITICAL CVSS 3.1
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
Description

llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.

INFO

Published Date :

April 1, 2026, 6:16 p.m.

Last Modified :

April 30, 2026, 7:18 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-34159 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.

ID Vendor Product Action
1 Ggml llama.cpp
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 CRITICAL [email protected]
CVSS 3.1 CRITICAL MITRE-CVE
Solution
Update llama.cpp to b8492 or later to fix memory corruption and RCE.
  • Update llama.cpp to version b8492 or later.
  • Ensure RPC backend is configured securely.
  • Disable RPC backend if not in use.
Public PoC/Exploit Available at Github

CVE-2026-34159 has a 4 public PoC/Exploit available at Github. Go to the Public Exploits tab to see the list.

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-2026-34159.

URL Resource
https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042 Patch
https://github.com/ggml-org/llama.cpp/pull/20908 Issue Tracking Patch
https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw Exploit Vendor Advisory
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-34159 is associated with the following CWEs:

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).

Critical buffer validation bypass in deserialize_tensor() (llama.cpp < b8492). Null tensor buffer skips bounds check, enabling unauthenticated arbitrary R/W via GRAPH_COMPUTE. ASLR bypass + RCE over TCP 50052.

Updated: 2 weeks, 3 days ago
0 stars 0 fork 0 watcher
Born at : May 4, 2026, 8:59 a.m. This repo has been linked 1 different CVEs too.

0 Click RCE exploit for CVE-2026-34159 Lama.cpp RPC server

Python

Updated: 3 weeks, 4 days ago
16 stars 8 fork 8 watcher
Born at : April 23, 2026, 9:14 p.m. This repo has been linked 1 different CVEs too.

Curated knowledge base tracking pickle deserialization vulnerabilities in ML frameworks. For GRC professionals and security teams.

Python

Updated: 3 weeks, 3 days ago
0 stars 0 fork 0 watcher
Born at : Jan. 18, 2026, 2:45 p.m. This repo has been linked 12 different CVEs too.

📡 PoC auto collect from GitHub. ⚠️ Be careful Malware.

security cve exploit poc vulnerability

Updated: 3 weeks, 5 days ago
7667 stars 1247 fork 1247 watcher
Born at : Dec. 8, 2019, 1:03 p.m. This repo has been linked 749 different CVEs too.

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

The following list is the news that have been mention CVE-2026-34159 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-34159 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.

  • Initial Analysis by [email protected]

    Apr. 30, 2026

    Action Type Old Value New Value
    Added CPE Configuration OR *cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:* versions up to (excluding) b8492
    Added Reference Type GitHub, Inc.: https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042 Types: Patch
    Added Reference Type GitHub, Inc.: https://github.com/ggml-org/llama.cpp/pull/20908 Types: Issue Tracking, Patch
    Added Reference Type GitHub, Inc.: https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw Types: Exploit, Vendor Advisory
  • New CVE Received by [email protected]

    Apr. 01, 2026

    Action Type Old Value New Value
    Added Description llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
    Added CWE CWE-119
    Added Reference https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
    Added Reference https://github.com/ggml-org/llama.cpp/pull/20908
    Added Reference https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
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.