CVE-2026-34159
CRITICAL EPSS 62.3%
Published Apr 1, 20263mo ago · Modified Jun 17, 20262w ago
9.8 CVSS 3.1
Published Apr 1, 2026 3mo ago
Last Modified Jun 17, 2026 2w ago
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality High
Integrity High
Availability High
Threat Intelligence
EPSS Exploit Probability
62.3% percentile
Exploit & Patch Status
Public Exploit Known
Patch Available
Weaknesses 1
CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer Memory Safety
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| ggml | llama.cpp | * | <b8492 |
References 3
- github.com https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
- github.com https://github.com/ggml-org/llama.cpp/pull/20908
- github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
Remediation
- github.com https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
- github.com https://github.com/ggml-org/llama.cpp/pull/20908