CVE-2025-63665

CriticalRCE

Published: 19 December 2025

Published

19 December 2025

Modified

05 January 2026

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 0.0043 34.1th percentile

Risk Priority 20 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-63665 is a critical-severity Code Injection (CWE-94) vulnerability in Gtedge Gt Edge Ai. Its CVSS base score is 9.8 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 34.1th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as Mobile/Edge AI; in the LLM/Generative AI Risks risk domain.

The strongest mitigations our analysis identified are NIST 800-53 SI-10 (Information Input Validation) and SI-2 (Flaw Remediation).

Deeper analysis

CVE-2025-63665 is a code injection vulnerability (CWE-94) affecting GT Edge AI Community Edition versions before v2.0.12. It enables attackers to execute arbitrary code by injecting a crafted JSON payload into the Prompt window. The issue 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), marking it as critical due to its network accessibility, low attack complexity, lack of required privileges or user interaction, and severe impacts across confidentiality, integrity, and availability.

Remote, unauthenticated attackers can exploit this vulnerability over the network without user interaction. By crafting and submitting a malicious JSON payload to the Prompt window, they achieve arbitrary code execution on the targeted system, potentially leading to full compromise.

Advisories from researcher p80n-sec detail the vulnerability, including proof-of-concept information. Mitigation requires upgrading to GT Edge AI Community Edition v2.0.12 or later, as earlier versions remain susceptible. Further technical details and reproduction steps are available at https://gist.github.com/p80n-sec/e5eefcef155e9dd14aaaaa49f9f94cd1 and https://github.com/p80n-sec/Vulnerability-Research/blob/main/CVE-2025-63665/CVE-2025-63665.md.

EU & UK References

🇪🇺 ENISA EUVD: EUVD-2025-204583

Vulnerability details

An issue in GT Edge AI Community Edition Versions before v2.0.12 allows attackers to execute arbitrary code via injecting a crafted JSON payload into the Prompt window.

CWE(s): CWE-94

AI Security AnalysisAI

AI Category: Mobile/Edge AI
Risk Domain: LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025: None mapped
Classification Reason: Matched keywords: ai

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 arbitrary code execution via crafted JSON payload injection into the Prompt window of the GT Edge AI Platform, consistent with exploitation of a public-facing application.