CVE-2026-57118
Received Received - Intake

Unauthenticated Agent Enumeration 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 1.6.59, AgentTeam.launch and the Agents alias register GET /{path}/list, POST /{path}, and `POST /{path}/{agent_id}' without access-control checks before listing agents or calling agent.chat. A remotely exposed server can therefore let unauthenticated clients enumerate agents, consume model resources, access connected private context, and trigger agent tools or workflow side effects. This vulnerability is fixed in praisonaiagents 1.6.59.

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-2026-57118
EUVD
EUVD-2026-97774

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
MervinPraison PraisonAI < 4.6.59
MervinPraison praisonaiagents < 1.6.59

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-862 The product does not perform an authorization check when an actor attempts to access a resource or perform an action.
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 in PraisonAI allows unauthenticated remote users to access three HTTP endpoints (GET /{path}/list, POST /{path}, POST /{path}/{agent_id}) without any access control checks. This enables attackers to list agents, invoke agent functions, consume model resources, and trigger side effects like accessing private context or executing tools.

Detection Guidance

To detect this vulnerability, check if your PraisonAI server exposes unauthenticated endpoints. Use curl to test GET /{path}/list, POST /{path}, and POST /{path}/{agent_id} without authentication. If these return agent details or execute actions, the system is vulnerable.

Impact Analysis

Unauthenticated attackers can enumerate agent IDs, trigger model usage, access connected private context, and execute agent tools or workflows. This may lead to unauthorized actions, data exposure, resource consumption, or side effects depending on deployed agents.

Compliance Impact

This vulnerability allows unauthenticated remote access to agent systems, enabling enumeration of agents, consumption of model resources, and execution of agent tools or workflows. This could lead to unauthorized data access, processing, or disclosure, violating GDPR principles of data protection and user consent, and HIPAA requirements for safeguarding protected health information.

Mitigation Strategies

Upgrade praisonaiagents to version 1.6.59 or later. Ensure AgentTeam.launch() binds to localhost (127.0.0.1) by default and enforce API key authentication for remote access. Block unauthenticated requests to the vulnerable endpoints.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-57118. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart