CVE-2026-44339

Summary

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 Software

Weaknesses

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

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: poc
  • Automatable: yes
  • Technical Impact: partial

Additional References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggq

References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggq

• ←Previous
• Next→