---
id: CVE-2026-57143
title: PraisonAI is a multi-agent teams system
summary: >-
  PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.62,
  searxng_search and the search_web SearxNG provider pass the LLM-controlled
  searxng_url parameter directly to requests.get without validating its scheme,
  host, port…
severity: high
cvss: 8.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:L'
cwe:
  - CWE-20
  - CWE-918
vendor: praisonaiagents
product: praisonaiagents
affected:
  - praisonaiagents < 1.6.61
patched:
  - praisonaiagents 1.6.61
published: '2026-10-12'
updated: '2026-10-16'
sourceUpdated: '2026-10-16T20:04:29.760'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-57143'
references:
  - url: >-
      https://github.com/MervinPraison/PraisonAI/commit/2a855c470077c7d2e2479a575f7ef7f548d51c33
    label: security-advisories@github.com
  - url: 'https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62'
    label: security-advisories@github.com
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4pcv-mg8v-vrgf
    label: security-advisories@github.com
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4pcv-mg8v-vrgf
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://github.com/MervinPraison/PraisonAI'
tags:
  - nvd
  - osv
  - pip
  - cve.org
  - exploit-available
epss: 0.00275
epssPercentile: 0.19838
aliases:
  - GHSA-4pcv-mg8v-vrgf
ecosystem: pip
exploitAvailable: true
ssvc:
  exploitation: poc
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-10-13T15:50:20.990896Z'
ingestedAt: '2026-07-21T19:04:56.252Z'
---

## Overview

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.62, searxng_search and the search_web SearxNG provider pass the LLM-controlled searxng_url parameter directly to requests.get without validating its scheme, host, port, or resolved address. Prompt-injected content can direct the default search tool to internal JSON services, distinguish open and closed internal ports, and attempt cloud-metadata requests, with returned JSON results entering agent context. This issue is fixed in praisonaiagents 1.6.62.

## Remediation

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

## Package advisory (CVE-2026-57143)

Affected packages:

- `praisonaiagents < 1.6.61`

Patched in:

- `praisonaiagents 1.6.61`

Source: https://osv.dev/vulnerability/GHSA-4pcv-mg8v-vrgf