PPTAgent versions before commit 418491a9a1c02d9d93194b5973bb58df35cf9d00 are vulnerable to arbitrary code execution due to improper neutralization of directives in dynamically evaluated code (CWE-95). The vulnerability arises because the software uses Python's eval() function to execute code generated by a large language model (LLM) with builtins accessible, enabling an attacker to execute arbitrary code. This issue was addressed and patched in commit 418491a.

Successful exploitation allows an attacker to execute arbitrary code with the privileges of the PPTAgent process, potentially leading to complete compromise of the affected system. The CVSS v3.1 score is 8.6 (high), reflecting local attack vector, low attack complexity, no privileges required, user interaction required, scope changed, and high impact on confidentiality, integrity, and availability.

A patch fixing this vulnerability is available in commit 418491a of the PPTAgent codebase. Users should update to this commit or later to remediate the issue. Since this is not a cloud service, remediation depends on applying this update. No additional mitigation guidance is provided by the vendor advisory. Patch status is not explicitly stated beyond the commit reference; verify the update from the official repository.