What is the CVSS score of CVE-2025-49847?

CVE-2025-49847 has a CVSS 3.1 base score of 8.8 (High). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.2%.

How to fix or mitigate CVE-2025-49847?

Within 24 hours: inventory all systems running llama.cpp and identify those in production or handling sensitive data; isolate affected systems from critical networks if patching cannot be completed immediately. Within 7 days: apply vendor patch to version b5662 or later across all affected systems; validate patches in test environments first. Within 30 days: conduct security audit of model sources and implement controls to restrict model loading to trusted, verified sources only; review access logs for suspicious model uploads or executions.

Llama.Cpp CVE-2025-49847

Q: Which versions of Llama.Cpp are affected by CVE-2025-49847?

A critical vulnerability in llama.cpp allows attackers to execute arbitrary code by crafting malicious AI model files, potentially compromising any system using this library for language model…. A patch is available.

EUVD-2025-18632 HIGH

Buffer Overflow (CWE-119)

2025-06-17 security-advisories@github.com

RCE Buffer Overflow Llama.Cpp Llama Cpp Suse Ggml

8.8

CVSS 3.1 · GitHub Advisory

View

Vulnerability Assessment

Weakness	CWE CWE-119 OWASP Top 10:2025 A06:2021 - Vulnerable and Outdated Components ASVS 5.0 V15 - Secure Coding and Architecture Bounds checking, buffer size validation MITRE ATT&CK 2 techniques across 2 tactics: Execution, Privilege Escalation The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up. Sign in to read
Impact	CVSS 8.8. EPSS 0.2%. Vendor patch available.
Exploit ScenarioDerived	An attacker could exploit this vulnerability in llama.cpp to compromise the security of affected deployments, potentially impacting confidentiality, integrity, or availability.

This Week Schedule remediation this week. Why: HIGH severity (CVSS 7.0-8.9).

Patch available 0.2% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Mar 14, 2026

A buffer overflow vulnerability in llama.cpp (CVSS 8.8). High severity vulnerability requiring prompt remediation. Vendor patch is available.

Earlier versions of this analysis (1)

v1 Mar 14, 2026 - 22:15 CVSS 8.8

RemediationAI

Apply the vendor-supplied patch immediately. Consider network segmentation to limit exposure if patching is delayed.

Affected VersionsENISA

llama.cpp < b5662

Affects your stack

Find out whether the stacks and servers you run are on an affected version.

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Technical ContextAI · show details

CWE-119 (Buffer Overflow). CVSS 8.8 indicates high severity. Affects llama.cpp.

Know when Llama.Cpp gets its next vulnerability

Watch products and get an email when something new is published
Check this CVE against your own stack and servers
Exploit and PoC references, threat intelligence from 22 sources

Continue with Google Continue with GitHub

No credit card · 7-day full trial

Severity by source

GitHub Advisory PRIMARY 8.8 HIGH

AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Ubuntu MEDIUM

SUSE HIGH

Primary rating from GitHub Advisory.

CVSS VectorGitHub Advisory

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Patch released

Mar 14, 2026 - 22:15 nvd

Patch available

CVE Published

Jun 17, 2025 - 20:15 nvd

HIGH 8.8

DescriptionGitHub Advisory

llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662.

Executive ViewAI

Why It Matters

A critical vulnerability in llama.cpp allows attackers to execute arbitrary code by crafting malicious AI model files, potentially compromising any system using this library for language model inference. Organizations deploying llama.cpp in production environments face immediate risk of data breach, service disruption, and unauthorized system access.

Business Impact: High

Compensating Controls

Apply vendor patch. Interim mitigations if patching is delayed: (1) restrict llama.cpp to offline/air-gapped environments with only pre-validated models; (2) implement strict file integrity monitoring on GGUF model files; (3) run llama.cpp processes with minimal privileges and in sandboxed containers; (4) disable remote model loading and only allow local, pre-screened models; (5) implement network segmentation to limit lateral movement from compromised inference processes.

Threat Intelligence Overview

EPSS Score

0.2%

Top 58% exploitable

Data Quality

6 sources

Confidence: High

EUVD

NVD

CVE.org

EPSS Vendor

GitHub

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue

Severity HIGH

CISA KEV No

Public POC No

EPSS 0.2%

Patch available Yes

Active threat No

Deciding rule

HIGH severity (CVSS 7.0-8.9)

What every action level means

Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.

Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.

This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.

This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.

Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision· derived

Scheduled

Exploitation· derived

None

System Exposure· derived

Open

Automatable· derived

Human Impact

High

Priority Score

Low Medium High Critical

KEV: 0

EPSS: 0

CVSS: +44

PoC: 0

Weaponized: 0

Threat intel: 0

Gov advisory: 0

Attack Technique

Buffer Overflow HIGH

A buffer overflow occurs when a program writes more data to a memory buffer than it was allocated to hold, causing the excess data to spill into adjacent memory regions.

Remote Code Execution CRITICAL

Remote Code Execution represents the critical moment when an attacker successfully runs arbitrary code on a target system without physical access.