---
id: CVE-2026-57125
title: PraisonAI is a multi-agent teams system
summary: >-
  PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and
  praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts
  attacker-controlled agent_yaml, and the approve field can mark execute_command
  as YAML-…
severity: critical
cvss: 9.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-306
  - CWE-863
vendor: MervinPraison
product: PraisonAI
affected:
  - PraisonAI < 4.6.59
  - praisonaiagents < 1.6.59
patched:
  - praisonai 4.6.59
  - praisonaiagents 1.6.59
published: '2026-09-14'
updated: '2026-09-15'
sourceUpdated: '2026-09-15T14:45:28.563'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-57125'
references:
  - url: >-
      https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9
    label: security-advisories@github.com
  - url: 'https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59'
    label: security-advisories@github.com
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x
    label: security-advisories@github.com
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://github.com/MervinPraison/PraisonAI'
tags:
  - nvd
  - cve.org
  - osv
  - pip
  - exploit-available
epss: 0.00601
epssPercentile: 0.46501
aliases:
  - GHSA-4869-x4pr-q22x
ecosystem: pip
exploitAvailable: true
ssvc:
  exploitation: poc
  automatable: 'yes'
  technicalImpact: total
  timestamp: '2026-09-14T19:18:10.875460Z'
ingestedAt: '2026-07-21T19:04:56.213Z'
---

## Overview

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.

## Package advisory (CVE-2026-57125)

Affected packages:

- `praisonai < 4.6.59`
- `praisonaiagents < 1.6.59`

Patched in:

- `praisonai 4.6.59`
- `praisonaiagents 1.6.59`

Source: https://osv.dev/vulnerability/GHSA-4869-x4pr-q22x