Skip to main content

CVE-2026-57125: CWE-306: Missing Authentication for Critical Function in MervinPraison PraisonAI

0
Critical
VulnerabilityCVE-2026-57125cvecve-2026-57125cwe-306cwe-863
Published: 09/14/2026 (09/14/2026, 14:19:42 UTC)
Source: CVE Database V5
Vendor/Project: MervinPraison
Product: PraisonAI

Description

PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.

CVSS v3.1

Score 9.8critical

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Affected software

MervinPraison

PraisonAI

Affected versions
<4.6.59

MervinPraison

praisonaiagents

Affected versions
<1.6.59
GitHub Actionsmore threats →ai
mervinpraison/PraisonAI
pkg:github/mervinpraison/PraisonAI
Affected versions
<4.6.59
GitHub Actionsmore threats →ai
mervinpraison/praisonaiagents
pkg:github/mervinpraison/praisonaiagents
Affected versions
<1.6.59

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/14/2026, 14:46:42 UTC

Technical Analysis

CVE-2026-57125 describes a missing authentication vulnerability (CWE-306) in MervinPraison's PraisonAI multi-agent system. Before versions 4.6.59 (PraisonAI) and 1.6.59 (praisonaiagents), the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled YAML input. The approve field can be manipulated to mark execute_command as approved, bypassing the @require_approval checks on critical tools. This allows remote attackers to invoke arbitrary OS commands via a configured language model agent without any credentials or operator interaction. The issue is resolved in the specified fixed versions.

Potential Impact

An unauthenticated remote attacker can execute arbitrary operating system commands on the affected system, leading to full compromise (confidentiality, integrity, and availability impacts are all high). This is a critical security risk due to the lack of authentication and the ability to bypass approval mechanisms.

Mitigation Recommendations

Upgrade PraisonAI to version 4.6.59 or later and praisonaiagents to version 1.6.59 or later to apply the official fix. These versions contain patches that enforce proper authentication and approval checks, mitigating the vulnerability.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-06-24T00:33:17.707Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6aa8057055bf5e2cf52f81b8

Added to database: 09/14/2026, 14:32:16 UTC

Last enriched: 09/14/2026, 14:46:42 UTC

Last updated: 09/15/2026, 03:10:00 UTC

Views: 11

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses