CVE-2026-44339
With the default agent configuration, _perm_allow is None, so undeclared non-dangerous tool names are not rejected by the permission gate.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.36%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 8.6 HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L
- EPSS
- 0.36% probability · 30th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-470
- Affected
- praison/praisonai · praison/praisonaiagents
- Source
- security-advisories@github.com
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggqExploit, Vendor Advisory
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggqExploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.