CVE-2026-44339
HIGH
8,6
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Scope: unchanged
Confidentiality: low
Integrity: high
Availability: low
Description
AI Translation Available
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.
470
Use of Externally-Controlled Input to Select Classes or Code ('Unsafe Reflection')
DraftCommon Consequences
Security Scopes Affected:
Integrity
Confidentiality
Availability
Other
Potential Impacts:
Execute Unauthorized Code Or Commands
Alter Execution Logic
Dos: Crash, Exit, Or Restart
Other
Read Application Data
Applicable Platforms
Languages:
Interpreted, Java, PHP
Application
Praisonaiagents by Praison
Version Range Affected
To
1.6.37
(exclusive)
CPE Identifier
View Detailed Analysis
cpe:2.3:a:praison:praisonaiagents:*:*:*:*:*:python:*:*
Common Platform Enumeration - Standardized vulnerability identification
Application
Praisonai by Praison
Version Range Affected
To
4.6.37
(exclusive)
CPE Identifier
View Detailed Analysis
cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*
Common Platform Enumeration - Standardized vulnerability identification
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-q…
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-q…