Vulnerability details

CVE-2026-34159

ggml-org llama.cpp

llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

CVSS 3.1

9.8Critical

Official 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 scores

Score	Version	Source	Vector
9.8Critical	3.1	CVEProject cvelistV5 (CNA) (GitHub_M)	`CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`

Affected products

Vendor	Product	Versions	Source
ggml-org	llama.cpp	< b8492	CVEProject cvelistV5 (CNA)

References and advisories

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw x_refsource_CONFIRM
https://github.com/ggml-org/llama.cpp/pull/20908 x_refsource_MISC
https://github.com/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042 x_refsource_MISC

Kolun on Telegram @kolunsec Exploited CVEs, key news and a daily digest Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.

Details

Published: 2026-04-01
Last updated: 2026-04-02
State: Published
Assigner (CNA): GitHub_M

Exploit prediction (EPSS)

1.62%

Probability of exploitation in 30 days

76.2%

Percentile (among all CVEs)

SSVC assessment (CISA)

Automatable: Yes
Exploitation: Proof of concept
Technical impact: Total

Weaknesses (CWE)

CWE-119
Improper Restriction of Operations within the Bounds of a Memory Buffer