CVE 7.9 HIGH

PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls_CVE-2026-40149

7.9 / 10
HIGH
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N

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.

Basic Information

ID CVE-2026-40149
Source GitHub_M
Published Apr 9, 2026 at 21:23
Modified Apr 9, 2026 at 21:28

Affected Product

Vendor MervinPraison
Product PraisonAI
Version < 4.5.128
Affected Versions MervinPraison PraisonAI < 4.5.128

CWE Classification

References

💭 Join the Security Discussion

🔒 Your email address will not be published. Required fields are marked *

⚠️ Please be respectful and constructive in your comments. Security discussions should remain professional.