CVE-2026-34159 | llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend

Exp

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.

Published: 2026-04-01 Last update: 2026-04-30 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-34159 is rated High Exploit Risk (75.8/100): CVSS Critical severity, with medium exploitation likelihood (EPSS 0.42%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2026-34159

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2026-34159

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-08 0.53% 0.42% -0.12%
2 2026-05-26 0.72% 0.53% -0.19%
3 2026-05-13 — 0.72% —

Full EPSS history (6 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-34159

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]

Weakness enumeration for CVE-2026-34159

OS Trackers for CVE-2026-34159

vendor priority summary link
debian not yet assigned CVE-2026-34159 not yet assigned priority: Debian including 1 source packages (llama.cpp), 2 status rows across 2 suites (forky, sid): resolved 2. https://security-tracker.debian.org/tracker/CVE-2026-34159
ubuntu medium CVE-2026-34159 medium priority: Ubuntu including 1 source packages (llama.cpp), 5 status rows across 5 suites (jammy, noble, questing, resolute, upstream): DNE 2, needs-triage 1, not-affected 1, released 1. https://ubuntu.com/security/CVE-2026-34159

Affected software / configurations for CVE-2026-34159

Vendor Product Version Raw CPE
ggml llama.cpp < b8492 cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*

References for CVE-2026-34159

cvelogic Threat Intelligence