cve.bz

CVE-2026-34159 ggml llama.cpp

9.8 criticalExploit referenceEPSS 1.6%Fix available

Critical (9.8) in ggml llama.cpp. EPSS 1.6% estimated probability of exploitation activity in the next 30 days.

On this page
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.

Severity

CVSS 3.1

9.8 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS
1.6% (unchanged from 1.6% a week ago; 1.2% 30 days ago) estimated probability of exploitation activity in the next 30 days; 77th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: yes · Technical impact: total, assessed 2026-04-01. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-34159 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-34159?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-34159?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-34159 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
ggml:llama.cppbefore b8492

Linux distributions

DistributionReleasePackageFixed inAdvisory
Debian14llama.cpp8611+dfsg-1DEBIAN-CVE-2026-34159
Ubuntu25.10llama.cppno fix listedUBUNTU-CVE-2026-34159

From the distributions' data via OSV.dev: the Debian Security Tracker; Ubuntu Security Notices © Canonical Ltd., CC BY-SA 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: Debian · Ubuntu.

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.

Attack patterns (CAPEC)

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-119 (12).

References

Check your stackJSON