CVE-2026-57140
Received Received - Intake

Authentication Bypass in PraisonAI AgentOS

Publication date: 2026-09-15

Last updated on: 2026-09-15

Assigner: GitHub, Inc.

Description
PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/src/os/config.ts and registers GET /api/agents and POST /api/chat without authentication middleware. A remote caller who can reach the service can obtain agent names, roles, and instruction prefixes and can invoke a selected agent, potentially reaching its tools, memory, external APIs, credentials, and workflow state. An initial remediation was released in version 1.7.2.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-15
Last Modified
2026-09-15
Generated
2026-09-15
AI Q&A
2026-09-15
EPSS Evaluated
N/A
NVD
CVE-2026-57140
EUVD
EUVD-2026-78394

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
praisonai praisonai From 1.6.0 (inc) to 1.7.2 (inc)
agentos agentos From 1.6.0 (inc) to 1.7.2 (inc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-306 The product does not perform any authentication for functionality that requires a provable user identity or consumes a significant amount of resources.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability affects PraisonAI versions 1.6.0 to 1.7.1. The AgentOS HTTP server binds to all network interfaces (0.0.0.0) by default and exposes sensitive routes without authentication. Attackers can access GET /api/agents to list agent names, roles, and instructions, and use POST /api/chat to invoke agents without credentials. This allows unauthorized access to agent tools, memory, APIs, credentials, and workflow state.

Detection Guidance

Check if the PraisonAI service is running on your system by inspecting running processes for praisonai or agentos. Use network scanning tools like netstat or ss to verify if the service is listening on 0.0.0.0 and exposed ports. Inspect configuration files for default host settings and exposed API endpoints like /api/agents and /api/chat.

Impact Analysis

An attacker who can reach the service may obtain sensitive agent details and invoke agents with potential access to tools, memory, external APIs, credentials, and workflow state. This could lead to data exposure, unauthorized actions, or system compromise depending on agent permissions.

Compliance Impact

This vulnerability could lead to unauthorized access to sensitive data, violating GDPR's data protection principles and HIPAA's security requirements for protected health information. Unauthorized agent invocation may result in data breaches or improper data handling.

Mitigation Strategies

Upgrade to PraisonAI version 1.7.2 or later to apply the fix. Change the default host binding from 0.0.0.0 to 127.0.0.1 in the configuration. Add authentication middleware to the exposed API routes /api/agents and /api/chat. Restrict network access to the service using firewalls or network policies.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-57140. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart