Home

Description

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.

PUBLISHED Reserved 2026-05-05 | Published 2026-05-08 | Updated 2026-05-08 | Assigner GitHub_M




HIGH: 8.6CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L

Problem types

CWE-470: Use of Externally-Controlled Input to Select Classes or Code ('Unsafe Reflection')

Product status

praisonaiagents < 1.6.37
affected

praisonai < 4.6.37
affected

References

github.com/...isonAI/security/advisories/GHSA-gmjg-hv98-qggq exploit

github.com/...isonAI/security/advisories/GHSA-gmjg-hv98-qggq

cve.org (CVE-2026-44339)

nvd.nist.gov (CVE-2026-44339)

Download JSON