What’s Vulnerable › Vulnerabilities

CVE-2026-44339: PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

• Severity: high (CVSS 8.6 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.4% probability of exploitation in the next 30 days
• Public exploit or detection template: yes
• Published: 2026-05-08 · updated 2026-10-26
• Weakness: CWE-470

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.

Affected products

• MervinPraison PraisonAI: before 4.6.37 — fixed in 4.6.37
• MervinPraison praisonaiagents: before 1.6.37 — fixed in 1.6.37

How to fix

Upgrade to a fixed version: MervinPraison PraisonAI 4.6.37; MervinPraison praisonaiagents 1.6.37. Check the vendor advisory for mitigations.

References

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

Get alerted when CVE-2026-44339 or the next vulnerability affects your stack