Dashboard / CVE-2026-34159

CVE-2026-34159

CRITICAL
INFO Priority: 0.16 BB Relevance: 80/100
Published: 2026-04-01 Modified: 2026-10-26 First seen: 2026-10-29 Status: active

Attack Surface

Network Low Complexity No Auth No Interaction Conf. Impact Integ. Impact

CVSS Vector Breakdown

AV: Network
AC: Low
PR: None
UI: None
S: Unchanged
C: High
I: High
A: High

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.

Weakness Classification (1)

Affected Software (1)

VendorProductVersion
ggml llama.cpp < b8492

References & Advisories (3)

Bug Bounty Relevance

80 / 100
✓ Network accessible
✓ No authentication
✓ Low complexity
✓ No user interaction

CVSS Score

9.8 / 10.0 v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS — Exploitation Probability

1.62%
Raw Score 0.016230
Percentile 76.0%
Date 2026-10-29

EPSS Trend

2026-10-29
0.01623
2026-10-28
0.01594

Intelligence Sources

nvd ref →

External Links