---
id: CVE-2026-57112
title: PraisonAI is a multi-agent teams system
summary: >-
  PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until
  1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in
  src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts
  SseServerTransport on the legac…
severity: high
cvss: 8.3
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H'
cwe:
  - CWE-306
  - CWE-346
  - CWE-862
vendor: MervinPraison
product: PraisonAI
affected:
  - 'PraisonAI >= 3.10.0, < 4.6.59'
  - 'praisonaiagents >= 0.6.0, < 1.6.59'
patched:
  - praisonaiagents 1.6.59
  - praisonai 4.6.59
published: '2026-09-15'
updated: '2026-09-16'
sourceUpdated: '2026-09-16T18:17:09.877'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-57112'
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-vmf9-xx9w-86wx
    label: security-advisories@github.com
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmf9-xx9w-86wx
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://github.com/MervinPraison/PraisonAI'
tags:
  - nvd
  - cve.org
  - exploit-available
  - osv
  - pip
exploitAvailable: true
ssvc:
  exploitation: poc
  automatable: 'no'
  technicalImpact: total
  timestamp: '2026-09-16T17:51:49.084581Z'
epss: 0.00224
epssPercentile: 0.11587
aliases:
  - GHSA-vmf9-xx9w-86wx
ecosystem: pip
ingestedAt: '2026-07-21T19:04:57.715Z'
---

## Overview

PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-agents/praisonaiagents/mcp/mcp_server.py mounts SseServerTransport on the legacy /sse and /messages/ endpoints without default Host, Origin, or authentication enforcement. A malicious website can use DNS rebinding against a reachable local or internal SSE server, supply attacker-controlled Host and Origin headers, enumerate registered tools, and invoke them with the server user's privileges. The Streamable HTTP transport rejects the same hostile Origin, which isolates the flaw to the legacy SSE wrapper. An initial remediation was released in praisonaiagents 1.6.59 and PraisonAI 4.6.59.

## Remediation

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

## Package advisory (CVE-2026-57112)

Affected packages:

- `praisonaiagents >= 0.6.0, < 1.6.59`
- `praisonai >= 3.10.0, < 4.6.59`

Patched in:

- `praisonaiagents 1.6.59`
- `praisonai 4.6.59`

Source: https://osv.dev/vulnerability/GHSA-vmf9-xx9w-86wx