Connect your agent
AdvisoriesCriticalCheck your lockfilePluginHow it worksPricing Connect your agent

Advisory record · GHSA-6v92-r5mx-h5fx

smolagents has Sandbox Escape Vulnerability in the local_python_executor.py Module

CVSS 7.6 HighCriticalEPSS 0.31 · 98th percentile

Critical, because:

  • CVSS score 7.6 (7.0 or more) and EPSS 0.31 (0.1 or more): a high score and a real chance of exploitation in the next 30 days.

How we decide what’s critical

Published by the GitHub Advisory Database at 29 Jun 2026, 11:50 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

PackageEcosystemAffectedFixed in
smolagentsPyPI<1.17.01.17.0
Identifiers
GHSA-6v92-r5mx-h5fx · CVE-2025-5120 · PYSEC-2026-542
Weakness (CWE)
CWE-94
Tags
Published
29 Jun 2026
Updated
1 Jul 2026

Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

smolagents versions before 1.17.0 are affected by a sandbox escape in the local_python_executor.py module. An attacker who can supply code to be run by the agent's local Python executor can use whitelisted modules and functions to get past the restricted environment and run arbitrary code on the host. Upgrade smolagents to version 1.17.0 or later.

Written 10 Nov 2026.

Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

Severity and exploitation

ScoreRatingCVSSVectorSource
7.6 High 3.0 CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L CNA (@huntr_ai)
  • CISA KEV Not listed.
  • EPSS 0.31, the 98th percentile, on 13 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

Timeline

This record came from the full history of the GitHub Advisory Database, published 29 Jun 2026. New records show when each source confirmed them.

Sources

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.