CVE-2026-57133
Received Received - Intake

Command Injection in PraisonAI

Vulnerability report for CVE-2026-57133, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-09-15

Last updated on: 2026-09-15

Assigner: GitHub, Inc.

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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-15
Last Modified
2026-09-15
Generated
2026-09-15
AI Q&A
2026-09-15
EPSS Evaluated
N/A
NVD
EUVD

Affected Vendors & Products

Showing 4 associated CPEs
Vendor Product Version / Range
praisonai praisonai From 1.5.1 (inc) to 1.7.2 (inc)
mervinpraison praisonai 1.5.1
mervinpraison praisonai 1.7.1
mervinpraison praisonai From 1.7.2 (inc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-78 The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
CWE-863 The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.
CWE-693 The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability exists in PraisonAI versions 1.5.1 to 1.7.2. The shell() helper function only checks the first command token against a safe list but then executes the full command string via child_process.exec(). Attackers can bypass restrictions by appending malicious commands using shell metacharacters like semicolons, leading to arbitrary command execution with PraisonAI privileges.

Detection Guidance

To detect this vulnerability, inspect PraisonAI installations for versions between 1.5.1 and 1.7.1. Check if the utility-tools.shell() function is exposed to untrusted input. Review command execution logs for patterns like semicolon-separated commands (e.g., 'echo ok; printf <marker>').

Commands to check version: grep -r '"version": "1.[5-7].[0-9]"' /path/to/praisonai. Look for shell() usage in src/praisonai-ts/src/tools/utility-tools.ts.

Impact Analysis

An attacker could exploit this to execute arbitrary commands with the same privileges as the PraisonAI process. This may allow reading sensitive files, modifying system state, running unauthorized tools, exfiltrating data over the network, or causing denial of service. The impact depends on the process permissions and exposed functionality.

Compliance Impact

This vulnerability could lead to unauthorized data access or modification, violating GDPR's integrity and confidentiality principles or HIPAA's safeguards for protected health information. Organizations using affected versions may face compliance violations, legal penalties, and reputational damage due to insufficient command execution controls.

Mitigation Strategies

Upgrade PraisonAI to version 1.7.2 or later immediately. If upgrading is not possible, modify the shell() function to avoid passing full command strings to child_process.exec(). Use execFile() or spawn() with shell: false instead.

Restrict access to the shell() function to trusted users only. Review and audit all command executions in PraisonAI logs for suspicious patterns like command chaining.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-57133. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart