CVE-2026-42079

Deferred Deferred - Pending Action

Arbitrary Code Execution in PPTAgent via Python eval()

Publication date: 2026-05-04

Last updated on: 2026-05-04

Assigner: GitHub, Inc.

Description

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval() of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-05-04

Last Modified

2026-05-04

Generated

2026-07-06

AI Q&A

2026-05-05

EPSS Evaluated

2026-07-05

NVD

CVE-2026-42079

EUVD

EUVD-2026-27015

Affected Vendors & Products

Currently, no data is known.

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-95	The product receives input from an upstream component, but it does not neutralize or incorrectly neutralizes code syntax before using the input in a dynamic evaluation call (e.g. "eval").

Attack-Flow Graph

Executive Summary

The vulnerability in PPTAgent involves arbitrary code execution caused by the use of Python's eval() function on code generated by a large language model (LLM). Before a specific patch (commit 418491a), the eval() function was called with builtins in scope, allowing maliciously crafted code to execute arbitrary commands.

Impact Analysis

This vulnerability can lead to an attacker executing arbitrary code on the system running PPTAgent. This can result in complete compromise of confidentiality, integrity, and availability of the affected system.

Mitigation Strategies

The vulnerability in PPTAgent has been patched via commit 418491a. To mitigate this vulnerability, you should update PPTAgent to a version that includes this commit.

Hi! I’m here to help you understand CVE-2026-42079. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70