CVE-2026-55538
Received Received - Intake

Authentication Bypass in PraisonAI Agents

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 4.6.51, praisonai serve agents parses config["api_key"] but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. Missing or incorrect bearer and X-API-Key values still reach agent execution. 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-2026-55538
EUVD
EUVD-2026-65514

Affected Vendors & Products

Showing 4 associated CPEs
Vendor Product Version / Range
praisonai praisonai to 4.6.58 (exc)
praisonai praisonai 4.6.58
mervinpraison praisonai 4.6.51
mervinpraison 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.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

The vulnerability in PraisonAI versions before 4.6.51 allows unauthenticated access to agent invocation routes despite the --api-key flag being configured. The praisonai serve agents command ignores the provided API key, leaving the /agents and /agents/{agent_name} endpoints exposed without authentication.

Detection Guidance

Check if PraisonAI versions before 4.6.51 are running by inspecting the version output of praisonai serve agents. Verify if the --api-key flag is configured but ignored by testing unauthenticated access to /agents or /agents/{agent_name} endpoints using curl or similar tools.

Impact Analysis

This flaw enables unauthorized users to invoke agents, potentially leading to unauthorized LLM usage, data access, or tool execution. Attackers could exploit this to run agents without proper credentials.

Compliance Impact

This vulnerability allows unauthenticated access to agent invocation routes, potentially enabling unauthorized data access or tool execution. This could lead to violations of data protection requirements under GDPR (e.g., unauthorized processing of personal data) and HIPAA (e.g., unauthorized access to protected health information).

Mitigation Strategies

Upgrade PraisonAI to version 4.6.58 or later to ensure proper API key validation. If upgrading is not immediately possible, restrict network access to the agent invocation routes or disable them until patched.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-55538. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart