CVE-2026-57143
Received Received - Intake

Server-Side Request Forgery in PraisonAI

Publication date: 2026-10-12

Last updated on: 2026-10-12

Assigner: GitHub, Inc.

Description
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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-10-12
Last Modified
2026-10-12
Generated
2026-10-13
AI Q&A
2026-10-12
EPSS Evaluated
N/A
NVD
CVE-2026-57143
EUVD
EUVD-2026-97773

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
MervinPraison praisonaiagents < 1.6.62

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-20 The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
CWE-918 The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

PraisonAI is a multi-agent system where versions before 1.6.62 have a vulnerability in the searxng_search and search_web SearxNG provider. The issue is that the searxng_url parameter, controlled by the LLM, is passed directly to requests.get without validating its scheme, host, port, or resolved address. This allows prompt injection to manipulate the URL to access internal services or cloud metadata, potentially exposing sensitive data.

Detection Guidance

Check if your PraisonAI agents version is below 1.6.62. Inspect logs for unexpected outbound requests to internal or cloud metadata endpoints like 169.254.169.254. Monitor for prompt injection attempts in agent interactions.

Impact Analysis

This vulnerability could allow attackers to access internal JSON services, scan open ports, or attempt cloud-metadata requests. If successful, attackers might extract sensitive data from internal systems or cloud environments, which could then be used in further attacks or data breaches.

Compliance Impact

This vulnerability could lead to unauthorized access to internal services, potentially exposing sensitive data such as personal or health information. This may violate GDPR's data protection principles and HIPAA's requirements for safeguarding protected health information if such data is accessed or leaked.

Mitigation Strategies

Update PraisonAI to version 1.6.62 or later to address the vulnerability in searxng_search and search_web components.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-57143. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart