HighVulnerabilityLLM-specific

CVE-2025-9959: smolagents Local Python execution sandbox escape via dunder attributes

Source: NVD(opens in a new tab)
Identifier: CVE-2025-9959
Published: September 3, 2025
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.3%

Summary

CVE-2025-9959 is an incomplete validation of dunder attributes in smolagents' Local Python execution environment, which allows an attacker to escape the sandbox. The attack requires a prompt injection that tricks the agent into generating malicious code. The weakness is classified as CWE-94, Improper Control of Generation of Code ('Code Injection'), and JFrog is the cited source.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 7.6(high)
EPSS: 0.3%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

Weakness (CWE): CWE-94
Attack pattern (CAPEC): CAPEC-242
AI threat technique (MITRE ATLAS): AML.T0051

Affected

Vendors: HuggingFace

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-9959

First tracked: February 15, 2026 at 08:52 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Summary

Mitigation

Related items