Cyber Posture

CVE-2025-5120

CriticalPublic PoCRCE

Published: 27 July 2025

Published
27 July 2025
Modified
07 August 2025
KEV Added
Patch
CVSS Score 10.0 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
EPSS Score 0.0040 60.7th percentile
Risk Priority 20 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-5120 is a critical-severity Code Injection (CWE-94) vulnerability in Huggingface Smolagents. Its CVSS base score is 10.0 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Python (T1059.006); ranked in the top 39.3% 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 AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.

The strongest mitigations our analysis identified are NIST 800-53 AC-25 (Reference Monitor) and SC-18 (Mobile Code).

Threat & Defense at a Glance

What attackers do: exploitation maps to Python (T1059.006) and 1 other technique. What defenders deploy: see the NIST 800-53 controls recommended below.
Threat & Defense Details

Mitigating Controls (NIST 800-53 r5)AI

prevent

Requires confinement of mobile code, such as untrusted Python agent code, to approved execution domains, directly preventing sandbox escape and arbitrary code execution.

prevent

Mandates software-enforced separation and policy enforcement, addressing the inadequate static and dynamic checks in the local_python_executor.py module.

prevent

Implements a tamperproof reference monitor mediating all resource accesses, mitigating bypass of whitelisted modules and functions for RCE.

MITRE ATT&CK Enterprise TechniquesAI

T1059.006 Python Execution
Adversaries may abuse Python commands and scripts for execution.
T1211 Exploitation for Stealth Stealth
Adversaries may exploit vulnerabilities to evade detection by hiding activity, suppressing logging, or operating within trusted or unmonitored components.
Why these techniques?

The vulnerability enables attackers to bypass Python sandbox restrictions using whitelisted modules for arbitrary remote code execution, facilitating Python interpreter abuse (T1059.006) and exploitation to evade sandbox defenses (T1211).

NVD Description

A sandbox escape vulnerability was identified in huggingface/smolagents version 1.14.0, allowing attackers to bypass the restricted execution environment and achieve remote code execution (RCE). The vulnerability stems from the local_python_executor.py module, which inadequately restricts Python code execution despite employing static…

more

and dynamic checks. Attackers can exploit whitelisted modules and functions to execute arbitrary code, compromising the host system. This flaw undermines the core security boundary intended to isolate untrusted code, posing risks such as unauthorized code execution, data leakage, and potential integration-level compromise. The issue is resolved in version 1.17.0.

Deeper analysisAI

CVE-2025-5120 is a sandbox escape vulnerability affecting huggingface/smolagents version 1.14.0. The flaw resides in the local_python_executor.py module, which fails to adequately restrict Python code execution despite implementing static and dynamic checks. This allows attackers to leverage whitelisted modules and functions to execute arbitrary code, resulting in remote code execution (RCE) and undermining the intended isolation of untrusted code. The vulnerability carries a CVSS v3.1 base score of 10.0 (AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H) and is classified under CWE-94 (Improper Control of Generation of Code).

Attackers with network access can exploit this vulnerability without authentication or user interaction, bypassing the sandbox to achieve RCE on the host system. Successful exploitation enables unauthorized code execution, data leakage, and potential compromise at the integration level, fully breaching the security boundary designed to contain untrusted code.

The issue has been resolved in smolagents version 1.17.0, as detailed in the patching commit at https://github.com/huggingface/smolagents/commit/33a942e62b6fbf6a35d41f1c735bda2d64c163d0. Additional details are available on the Huntr bounty report at https://huntr.com/bounties/63ab1cfe-b573-4cf5-a7d3-fb6c957e34b0, which reported the vulnerability.

This vulnerability is particularly relevant in AI/ML contexts, as smolagents is part of the Hugging Face ecosystem for executing lightweight AI agents, where sandboxing untrusted code is critical for safe model and agent deployment. No public evidence of real-world exploitation has been reported.

Details

CWE(s)

Affected Products

huggingface
smolagents
1.14.0

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
huggingface/smolagents is a library for AI agents involving sandboxed Python code execution, fitting AI Agent Protocols and Integrations due to its focus on secure execution environments for agent tools and integrations.

CVEs Like This One

CVE-2026-4963Same product: Huggingface Smolagents
CVE-2026-2654Same product: Huggingface Smolagents
CVE-2024-12471Shared CWE-94
CVE-2026-25874Same vendor: Huggingface
CVE-2026-22807Shared CWE-94
CVE-2025-69902Shared CWE-94
CVE-2026-31040Shared CWE-94
CVE-2026-22793Shared CWE-94
CVE-2025-58176Shared CWE-94
CVE-2025-59528Shared CWE-94

References