cve.bz

CVE-2026-43629 ggml llama.cpp: Year 2038 problem, Y2K38, Y2038, Epochalypse

9.2 criticalEPSS 0.7%Fix available

Critical (9.2) in ggml llama.cpp. EPSS 0.7% estimated probability of exploitation activity in the next 30 days.

On this page
llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access to the slot_save_path directory to corrupt heap memory. Attackers can craft malicious state files where cell_count multiplication overflows or exceeds tensor buffer allocation to write attacker-controlled bytes past buffer boundaries, potentially resulting in heap metadata corruption, model weight corruption, or arbitrary code execution via function pointer overwrite.

Severity

CVSS 4.0

9.2 critical
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVSS 3.1

8.1 high
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS
0.7% (unchanged from 0.7% a week ago; 0.7% 30 days ago) estimated probability of exploitation activity in the next 30 days; 54th percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: no · Technical impact: total, assessed 2026-08-07. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-190 Integer Overflow or Wraparound (Year 2038 problem, Y2K38, Y2038, Epochalypse)
CWE-787 Out-of-bounds Write
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-43629 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-43629?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-43629?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-2026-43629 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 CNA's record in the CVE List.

ProductAffected
ggml-org llama.cppfrom b4882 through b9058

Linux distributions

DistributionReleasePackageFixed inAdvisory
Debian14llama.cppno fix listedDEBIAN-CVE-2026-43629
Ubuntu26.04:LTS, 26.10llama.cppno fix listedUBUNTU-CVE-2026-43629

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.

Red Hat

Red Hat rates this Important.

Red Hat's statement

Exploitation requires an attacker to possess write access to the slot storage location and plant a maliciously crafted key-value cache state file prior to a restoration operation. If successfully processed, the heap memory corruption can grant complete compromise of Confidentiality, Integrity, and Availability (C:H, I:H, A:H) within the context of the running application process. Environments that restrict file write access to state directories, utilize read-only session paths, or run stateless inference pipelines without state restore operations are completely unaffected.

Red Hat's mitigation

Restrict write access to the `slot_save_path` directory used by llama.cpp. Ensure that only trusted processes and users have permissions to write to this location. This prevents an attacker from introducing malicious KV cache state files that could trigger the heap buffer overflow. For deployments, consider running llama.cpp with the least necessary privileges and within a sandboxed environment to further limit the impact of potential file system compromises.

ProductPackageStateAdvisory
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-cuda-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Will not fix
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-rocm-rhel9Affected
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/disk-image-cuda-rhel9Affected

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-43629.

Attack patterns (CAPEC)

  • CAPEC-92 Forced Integer Overflow Likelihood: High · Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON