CVE-2026-44339
Published:May 08, 2026
Updated:August 06, 2026
PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and main after it fails to match the declared tool list and the registry. With the default agent configuration, _perm_allow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables that were never declared as tools. This issue has been patched in praisonai version 4.6.37 and praisonaiagents version 1.6.37.
Affected Packages
https://github.com/MervinPraison/PraisonAI.git (GITHUB):
Affected version(s) >=0.0.55 <4.6.37Fix Suggestion:
Update to version 4.6.37praisonaiagents (PYTHON):
Affected version(s) >=0.0.1 <1.6.37Fix Suggestion:
Update to version 1.6.37praisonai (PYTHON):
Affected version(s) >=0.0.1 <4.6.37Fix Suggestion:
Update to version 4.6.37Additional Notes
The description of this vulnerability differs from MITRE.
Related Resources (7)
Do you need more information?
Contact UsCVSS v4
Base Score:
8.8
Attack Vector
NETWORK
Attack Complexity
LOW
Attack Requirements
NONE
Privileges Required
NONE
User Interaction
NONE
Vulnerable System Confidentiality
LOW
Vulnerable System Integrity
HIGH
Vulnerable System Availability
LOW
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
8.6
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
LOW
Integrity
HIGH
Availability
LOW
Weakness Type (CWE)
Use of Externally-Controlled Input to Select Classes or Code ('Unsafe Reflection')
EPSS
Base Score:
0.36