What’s Vulnerable › Vulnerabilities

CVE-2026-40149: PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

• Severity: high (CVSS 7.3 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.2% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2026-04-09 · updated 2026-10-26
• Weakness: CWE-396

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.

Affected products

• MervinPraison PraisonAI: before 4.5.128 — fixed in 4.5.128

How to fix

Upgrade to a fixed version: MervinPraison PraisonAI 4.5.128. Check the vendor advisory for mitigations.

References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4wr3-f4p3-5wjh
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4wr3-f4p3-5wjh

Get alerted when CVE-2026-40149 or the next vulnerability affects your stack