CVE-2026-40149
PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls
- State
- Published
- Severity
- 7.9 High
- Published
- Apr 9, 2026
- Updated
- Apr 13, 2026
- Reserved
- Apr 9, 2026
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 3.1 | 7.9 High | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N | GitHub_M |
Weaknesses
- CWE-396 Declaration of Catch for Generic Exception
Affected Products
| Product | Versions |
|---|---|
PraisonAIMervinPraison |
|
References
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.