Description
PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g., shell_exec, file_write) to the allowlist, an attacker can cause the ExecApprovalManager to auto-approve all future agent invocations of those tools, bypassing the human-in-the-loop safety mechanism that the approval system is specifically designed to enforce. This vulnerability is fixed in 4.5.128.
Published: 2026-04-09
Score: 7.9 High
EPSS: < 1% Very Low
KEV: No
Impact: Remote Code Execution
Action: Patch Immediately
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories
Source ID Title
Github GHSA Github GHSA GHSA-4wr3-f4p3-5wjh PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls
History

Mon, 20 Apr 2026 20:00:00 +0000

Type Values Removed Values Added
First Time appeared Praison
Praison praisonai
CPEs cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*
Vendors & Products Praison
Praison praisonai

Mon, 13 Apr 2026 16:15:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}


Fri, 10 Apr 2026 09:00:00 +0000

Type Values Removed Values Added
First Time appeared Mervinpraison
Mervinpraison praisonai
Vendors & Products Mervinpraison
Mervinpraison praisonai

Thu, 09 Apr 2026 21:45:00 +0000

Type Values Removed Values Added
Description PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g., shell_exec, file_write) to the allowlist, an attacker can cause the ExecApprovalManager to auto-approve all future agent invocations of those tools, bypassing the human-in-the-loop safety mechanism that the approval system is specifically designed to enforce. This vulnerability is fixed in 4.5.128.
Title PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls
Weaknesses CWE-396
References
Metrics cvssV3_1

{'score': 7.9, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N'}


Subscriptions

Mervinpraison Praisonai
Praison Praisonai
cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-04-13T15:37:53.846Z

Reserved: 2026-04-09T19:31:56.013Z

Link: CVE-2026-40149

cve-icon Vulnrichment

Updated: 2026-04-13T15:27:02.496Z

cve-icon NVD

Status : Analyzed

Published: 2026-04-09T22:16:35.750

Modified: 2026-04-20T19:53:38.610

Link: CVE-2026-40149

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-04-10T09:28:51Z

Weaknesses