CVE-2026-57133 Details
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.
A command injection vulnerability has been identified in the PraisonAI npm package, specifically in versions 1.5.1 prior to 1.7.2. The issue arises in the 'shell()' function within the utility tools module, which is intended to execute safe, read-only shell commands. The function checks only the first word of the command against a allowlist of safe commands before passing the entire command string to 'child_process.exec()'. This oversight allows users to chain additional commands by exploiting shell metacharacters, thereby executing arbitrary commands with the same privileges as the PraisonAI process.
Users can update to PraisonAI version 1.7.2 or later, where this vulnerability has been fixed.
Metrics
CVSS 4.0 Severity and Vector Strings:
VolerionCVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Sep 15, 2026CISA-ADP
Assessed Sep 16, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj | CISA-ADP | AdvisoryExploitRemedyVendor |
| https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9 | [email protected] | Source CodeVendor |
| https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62 | [email protected] | Vendor |
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5jv7-2mjm-h6qj | [email protected] | AdvisoryExploitRemedyVendor |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-693 | Protection Mechanism Failure | [email protected] |
| CWE-78 | Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') | [email protected] |
| CWE-863 | Incorrect Authorization | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| MervinPraison/PraisonAI | >= 1.5.1, <= 1.7.1 (semver) |
CPE
Remediation
| |
| npm:praisonai | >= 1.5.1, <= 1.7.1 (semver) |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Sep 16, 2026 | CVE Modified | CISA-ADP |
| Sep 15, 2026 | New CVE Received | [email protected] |