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 !
Source :
[email protected]
CVSS Scores
| 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 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:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-34159
weaknesses.
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.
0 Click RCE exploit for CVE-2026-34159 Lama.cpp RPC server
Python
Curated knowledge base tracking pickle deserialization vulnerabilities in ML frameworks. For GRC professionals and security teams.
Python
📡 PoC auto collect from GitHub. ⚠️ Be careful Malware.
security cve exploit poc vulnerability
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