CVE-2026-55533
Received Received - Intake

Authentication Bypass in PraisonAI

Publication date: 2026-08-25

Last updated on: 2026-08-25

Assigner: GitHub, Inc.

Description
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, create_auth_middleware() allows requests when auth=api-key lacks PRAISONAI_API_KEY or JWT authentication lacks PRAISONAI_JWT_SECRET. An externally bound Recipe server can therefore accept unauthenticated POST /v1/recipes/run requests despite authentication being enabled. This issue is fixed in version 4.6.58.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-08-25
Last Modified
2026-08-25
Generated
2026-08-25
AI Q&A
2026-08-25
EPSS Evaluated
N/A
NVD
CVE-2026-55533
EUVD
EUVD-2026-65523

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
mervinpraison praisonai 4.6.58
praisonai praisonai 4.6.58

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.
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

PraisonAI is a multi-agent system where authentication is enforced via API keys or JWT secrets. A flaw in the authentication middleware allows requests to proceed even when these secrets are missing, bypassing security checks. This fail-open behavior lets unauthenticated users access protected endpoints like POST /v1/recipes/run.

Detection Guidance

Check if your PraisonAI instance is running a version before 4.6.58 by running: praisonai --version. Inspect server logs for POST requests to /v1/recipes/run or /v1/recipes/stream without authentication headers. Verify if API key or JWT secret environment variables (PRAISONAI_API_KEY, PRAISONAI_JWT_SECRET) are set in the deployment configuration.

Impact Analysis

An attacker could exploit this to trigger recipe workflows or administrative operations without authentication. This may lead to unauthorized actions, data leaks, or system manipulation if the Recipe server is exposed to external networks.

Compliance Impact

This vulnerability could violate compliance requirements for data protection (e.g., GDPR, HIPAA) by allowing unauthorized access to sensitive operations or data. Organizations must ensure proper authentication is enforced to meet regulatory controls for access management and audit logging.

Mitigation Strategies

Upgrade PraisonAI to version 4.6.58 or later immediately. Ensure PRAISONAI_API_KEY and PRAISONAI_JWT_SECRET are properly configured with strong secrets. Review and restrict network access to the Recipe server endpoints. Monitor for unauthorized POST /v1/recipes/run or /v1/recipes/stream requests in logs.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-55533. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart