Cyber Resilience

CVE-2024-6868

CriticalPublic PoC

Published: 29 October 2024

Published
29 October 2024
Modified
15 October 2025
KEV Added
—
Patch
—
CVSS Score v3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.0049 65.8th percentile
Risk Priority 20 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2024-6868 is a critical-severity Link Following (CWE-59) vulnerability in Mudler Localai. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 34.2% 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 Other Platforms; in the Supply Chain and Deployment risk domain; MITRE ATLAS techniques in scope: AI Supply Chain Compromise (AML.T0010), Exfiltration via AI Inference API (AML.T0024), External Harms (AML.T0048).

EU & UK References

Vulnerability details

mudler/LocalAI version 2.17.1 allows for arbitrary file write due to improper handling of automatic archive extraction. When model configurations specify additional files as archives (e.g., .tar), these archives are automatically extracted after downloading. This behavior can be exploited to perform…

more

a 'tarslip' attack, allowing files to be written to arbitrary locations on the server, bypassing checks that normally restrict files to the models directory. This vulnerability can lead to remote code execution (RCE) by overwriting backend assets used by the server.

CWE(s)
CWE-59NVD-CWE-noinfo

AI Security AnalysisAI

AI Category
Other Platforms
Risk Domain
Supply Chain and Deployment
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
LocalAI is an open-source platform for local AI model inference, providing a drop-in OpenAI-compatible REST API for self-hosted LLMs and other models, fitting 'Other Platforms' as it serves as an inference server/platform.

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

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 →
Why these techniques?

The vulnerability enables exploitation of the public-facing LocalAI server through improper archive extraction (tarslip), allowing arbitrary file writes outside the models directory and remote code execution by overwriting backend assets.

MITRE ATLAS TechniquesAI

MITRE ATLAS techniques

AML.T0010: AI Supply Chain CompromiseAML.T0024: Exfiltration via AI Inference APIAML.T0048: External Harms

Affected Assets

mudler
localai
2.17.1

Mitigating Controls

No mitigating controls mapped yet. The per-CVE control annotator has not reached this CVE.

References