CVEvulnerability
CVE-2026-44339
8.6 HIGH
Official page ↗
- Status
- Modified
- Published
- 2026-05-08
- Last modified
- 2026-10-26
- Assigner
- [email protected]
- CVSS 3.1 ([email protected])
- 8.6 HIGH — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L
- Weaknesses
- 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 configurations
• praison praisonai (< 4.6.37)
• praison praisonaiagents (< 1.6.37)
Related
Weakness · CWE (1)
- CWE-470 Use of Externally-Controlled Input to Select Classes or Code weakness
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggq Exploit, Vendor Advisory
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggq Exploit, Vendor Advisory