Cyber Resilience

CVE-2026-34159

Memory Safety in Ggml Llama.Cpp ≤ b8492

Public PoCMemory Safety
Published
01 April 2026
Modified
30 April 2026
Patch / advisory
View advisory
CVSS Score v3.1 9.8
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.011 63th percentile
Risk Priority 73 floored blend · peak EPSS

Summary

CVE-2026-34159 is a critical-severity Improper Restriction of Operations within the Bounds of a Memory Buffer (CWE-119) vulnerability in Ggml Llama.Cpp. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Process Injection (T1055); ranked in the top 37% 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; in the Protocol-Specific Risks risk domain.

The strongest mitigations our analysis identified map to SA-8 (Security and Privacy Engineering Principles) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2026-34159 is a critical vulnerability in llama.cpp, a C/C++ inference engine for large language models (LLMs). In versions prior to b8492, the RPC backend's deserialize_tensor() function skips all bounds validation when a tensor's buffer field is 0, enabling improper handling of memory buffers. This flaw, classified under CWE-119 (Improper Restriction of Operations within the Bounds of a Memory Buffer), carries a CVSS v3.1 base score of 9.8 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H).

An unauthenticated attacker with TCP access to the RPC server port can exploit this issue by sending crafted GRAPH_COMPUTE messages to read and write arbitrary process memory. When combined with pointer leaks obtainable via ALLOC_BUFFER and BUFFER_GET_BASE operations, attackers achieve full ASLR bypass, culminating in remote code execution. No privileges or user interaction are required, making it highly accessible over the network.

The vulnerability has been patched in llama.cpp version b8492. Official mitigation details are available in the GitHub security advisory (GHSA-j8rj-fmpv-wcxw), the fixing pull request (#20908), and the commit (39bf0d3c6a95803e0f41aaba069ffbee26721042), which recommend upgrading to the patched version to restore proper bounds checking in deserialize_tensor().

This issue is particularly relevant to AI/ML deployments relying on llama.cpp for efficient LLM inference, as exposed RPC servers could enable compromise of model-serving infrastructure. No public evidence of real-world exploitation has been reported as of the CVE publication on 2026-04-01.

EU & UK References

Vulnerability Data

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…

more

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.

CWE(s)
CWE-119

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Protocol-Specific Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llama.cpp, llm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1055 Process Injection Stealth
Adversaries may inject code into processes in order to evade process-based defenses as well as possibly elevate privileges.
attack.mitre.org →
T1068 Exploitation for Privilege Escalation Privilege Escalation
Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.
attack.mitre.org →
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.
attack.mitre.org →
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
attack.mitre.org →
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
attack.mitre.org →
T1212 Exploitation for Credential Access Credential Access
Adversaries may exploit software vulnerabilities in an attempt to collect credentials.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-52566Same product: Ggml Llama.Cpp
CVE-2025-49847Same product: Ggml Llama.Cpp
CVE-2026-33298Same product: Ggml Llama.Cpp
CVE-2024-42478Same product: Ggml Llama.Cpp
CVE-2024-23496Same product: Ggml Llama.Cpp
CVE-2024-21836Same product: Ggml Llama.Cpp
CVE-2024-42479Same product: Ggml Llama.Cpp
CVE-2026-21869Same product: Ggml Llama.Cpp
CVE-2024-21825Same product: Ggml Llama.Cpp
CVE-2024-23605Same product: Ggml Llama.Cpp

Affected Assets

ggml
llama.cpp
≤ b8492

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)
  • V17.3.2

Mitigating Controls (NIST 800-53 r5) AI

SA-8 Security and Privacy Engineering Principles partial match

Secure engineering principles require memory-safe design and coding that structurally avoids buffer-boundary violations.

SI-10 Information Input Validation partial match

Input validation directly enforces bounds checking that stops out-of-bounds reads/writes from being introduced or reached.

SI-16 Memory Protection partial match

Memory protection restricts exploitation impact of buffer overflows without eliminating the underlying coding flaw.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

Secure SDLC practices (bounds checking, safe APIs, reviews) directly prevent this class of flaw.

ID.RA-01 partial match
prevents

Vulnerability scanning and code analysis directly surface buffer-boundary flaws.

ID.RA-08 partial match
prevents

Receiving and triaging vulnerability disclosures commonly includes buffer-related reports.

PR.AT-02 partial match
prevents

Developer training on secure coding reduces introduction of memory-buffer errors.

PR.PS-02 partial match
prevents

Patching replaces vulnerable code containing buffer-boundary defects.

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

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

A.8.29 Security testing in development and acceptance mostly match
finds

Security testing in development catches out-of-bounds accesses before release, covering most instances of the weakness.

A.8.25 Secure development life cycle partial match
prevents

Secure development lifecycle mandates memory-safety practices that directly prevent buffer-boundary violations.

A.8.26 Application security requirements partial match
prevents

Application security requirements can specify memory-safety rules, but do not prescribe implementation details.

A.8.27 Secure system architecture and engineering principles partial match
prevents

Secure architecture and engineering principles include memory-safe design patterns that mitigate buffer overflows.

A.8.28 Secure coding partial match
prevents

Secure coding standards explicitly forbid unsafe buffer operations, directly eliminating CWE-119.

References