Security Resilience

CVE-2026-43629

Memory Safety in Ggml Llama.Cpp b4882 – b9058

Public PoCMemory Safety
Published
06 August 2026
Modified
29 October 2026
Patch / advisory
CVSS Score v4 9.2
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0070 53th percentile
Risk Priority 46 floored blend · peak EPSS

CVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). EPSS, Forum of Incident Response and Security Teams (FIRST), epss.first.org. Risk Priority is our own derived reading, not an NVD score.

Summary

CVE-2026-43629 is a critical-severity Integer Overflow or Wraparound (CWE-190) vulnerability in Ggml Llama.Cpp. Its CVSS base score is 9.2 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Endpoint Denial of Service (T1499); ranked in the top 47% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as NLP and Transformers.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SA-15 (Development Process, Standards, and Tools) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llama.cpp

Related Threats

MITRE ATT&CK Enterprise Techniques

MITRE ATT&CK v20.0

T1068 Exploitation for Privilege Escalation Privilege Escalation
Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.
T1189 Drive-by Compromise Initial Access
Adversaries may gain access to a system through a user visiting a website over the normal course of browsing.
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
T1212 Exploitation for Credential Access Credential Access
Adversaries may exploit software vulnerabilities in an attempt to collect credentials.
T1499 Endpoint Denial of Service Impact
Adversaries may perform Endpoint Denial of Service (DoS) attacks to degrade or block the availability of services to users.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2024-21825Same product: Ggml Llama.Cpp
CVE-2024-23496Same product: Ggml Llama.Cpp
CVE-2024-23605Same product: Ggml Llama.Cpp
CVE-2024-21836Same product: Ggml Llama.Cpp
CVE-2024-21802Same product: Ggml Llama.Cpp
CVE-2024-42479Same product: Ggml Llama.Cpp
CVE-2023-39125Shared CWE-190, CWE-787
CVE-2024-11236Shared CWE-190, CWE-787
CVE-2024-45555Shared CWE-190, CWE-787
CVE-2023-28537Shared CWE-190, CWE-787

Affected Assets

ggml
llama.cpp
b4882 — b9058

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

—

Detect
Catch it (NIST detect / respond)

—

Harden
Shrink the surface (DISA STIG)

—

Validate
Prove the fix (OWASP ASVS)
  • V5.2.6

Mitigating Controls (NIST 800-53 r5)

Our mappings, made for this CVE.

Developer testing and evaluation (static analysis, fuzzing, unit tests) directly finds integer overflow defects before deployment.

Requiring documented secure-development standards and tools can mandate bounds-checked coding practices that avoid the weakness.

Secure engineering principles require use of safe arithmetic constructs or language features that structurally eliminate integer overflow during calculation.

Input validation enforces bounds on values before arithmetic, stopping the conditions that trigger overflow or wraparound.

Memory-protection mechanisms limit the exploitability and blast radius of a successful out-of-bounds write.

Mitigating Controls (NIST CSF 2.0)

Our mappings, derived directly from the weakness types (CWEs) cited in the NVD entry via our CWE→CSF cross-walk — links open the control.

PR.PS-06 mostly match
blocks

Secure SDLC practices directly require use of safe arithmetic, bounds checks, and testing that prevent integer overflows.

ID.RA-01 partial match
blocks

Vulnerability scanning and recording can discover out-of-bounds write flaws so they can be remediated.

PR.PS-02 partial match
blocks

Patching or replacing vulnerable software directly eliminates known instances of this coding weakness.

Mitigating Controls (ISO/IEC 27001:2022 Annex A)

Our mappings, derived directly from the weakness types (CWEs) cited in the NVD entry via our CWE→ISO cross-walk — links open the control.

finds

Security testing in development can detect integer overflows before release.

prevents

Secure coding standards explicitly forbid unsafe integer operations and mandate overflow-safe constructs.

finds

A.8.8's reach is DISCLOSURE — it identifies vulnerabilities through vendor advisories, vulnerability scanning, and third-party component tracking. Integer overflows in third-party components with published CVEs are found (the observed examples include several), but the bulk of CWE-190 instances in first-party/custom code are not what A.8.8 reaches; those require source-reading testing (A.8.28/A.8.29). Same logic as the A.8.8 finds CWE-89 = partial anchor.

References