SEPTEMBER 16, 2026
Live Feed
Back to database
Case File

CVE-2026-57133

HIGH · CVSS 8.8 EPSS 0.44% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-09-15 · Last synced 2026-09-16

CyberRota Analysis

AI-Generated

The vulnerability in PraisonAI allows arbitrary command execution due to improper validation in the shell() helper, which only checks the first token of a command against a whitelist. This flaw can be exploited by attackers to execute unauthorized commands with the privileges of the PraisonAI process. Organizations using versions 1.5.1 to 1.7.1 should prioritize updating to version 1.7.2 to mitigate this high-severity risk.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-57133
Severity
HIGH
CVSS
8.8
EPSS
0.44%

Original NVD Description

PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2.