CVE-2026-40149
HIGH
MEDIUM
Priority: 0.02
BB Relevance:
40/100
Published: 2026-04-09
Modified: 2026-10-26
First seen: 2026-10-29
Status: active
Attack Surface
Low Complexity
No Interaction
Integ. Impact
Scope Change
CVSS Vector Breakdown
AV:
Local
AC:
Low
PR:
Low
UI:
None
S:
Changed
C:
Low
I:
High
A:
None
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.
Weakness Classification (1)
References & Advisories (1)
Exploit
Vendor Advisory