CVE-2026-57132
Received Received - Intake

PraisonAI Token Authentication Bypass in Agent Invocation

Publication date: 2026-09-14

Last updated on: 2026-09-14

Assigner: GitHub, Inc.

Description
PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAI_CALL_AUTH to disabled makes verify_token accept requests to /api/v1/agents/{id}/invoke without CALL_SERVER_TOKEN authentication. Deployments that use the application's advertised opt-out can expose registered agents and their connected tools or private context to unauthenticated invocation. The vulnerability is fixed in 4.6.62.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-14
Last Modified
2026-09-14
Generated
2026-09-15
AI Q&A
2026-09-14
EPSS Evaluated
N/A
NVD
CVE-2026-57132
EUVD
EUVD-2026-77596

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
praisonai praisonai to 4.6.62 (exc)
mervinpraison praisonai to 4.6.48|start_including=4.6.61 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-287 When an actor claims to have a given identity, the product does not prove or insufficiently proves that the claim is correct.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

CVE-2026-57132 is a vulnerability in PraisonAI versions prior to 4.6.62. When the environment variable PRAISONAI_CALL_AUTH is set to disabled, the application incorrectly allows unauthenticated access to the agent invocation API endpoint /api/v1/agents/{id}/invoke. This bypasses authentication requirements and exposes agents and their tools to unauthorized use.

Detection Guidance

Check if the environment variable PRAISONAI_CALL_AUTH is set to disabled in your PraisonAI deployment. Inspect configuration files or Docker/Compose environments for this setting. Verify if the /api/v1/agents/{id}/invoke endpoint is accessible without authentication by sending a test request to the endpoint.

Impact Analysis

This vulnerability allows attackers to invoke any agent without authentication, potentially leading to unauthorized actions, data exposure, or misuse of connected tools. Systems using the disabled authentication setting are at high risk of exploitation, especially if agents have access to sensitive data or functions.

Compliance Impact

This vulnerability likely violates compliance requirements for data protection and access control, such as GDPR's principle of least privilege and HIPAA's access control safeguards. Unauthorized access to agents and tools could result in data breaches, leading to regulatory penalties and loss of trust.

Mitigation Strategies

Upgrade PraisonAI to version 4.6.62 or later to patch the vulnerability. If upgrading is not immediately possible, remove or change the PRAISONAI_CALL_AUTH=disabled setting to enforce authentication. Ensure the /api/v1/agents/{id}/invoke endpoint requires valid authentication tokens.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-57132. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart