CVE-2026-44339 json
PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
published 2026-05-08 6 mo ago modified 2026-10-26 13 d ago also GHSA-gmjg-hv98-qggq , PYSEC-2026-2915 , PYSEC-2026-2948 , EUVD-2026-28642
- cvss
- 8.6
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 30%
- public exploits
- 0
- none known
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.
Patch / fix
- pypi praisonaiagents 1.6.37
- pypi praisonai 4.6.37
- praison praisonai 4.6.37
- praison praisonaiagents 1.6.37
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 6 mo ago
Exploit prediction
0.36% chance of exploitation in the next 30 days, higher than 30% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggq referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 8.6 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L |
| OSV | 3.1 | 8.6 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L |
| GitHub | 3.1 | 8.6 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | praisonaiagents | <1.6.37 |
1.6.37 |
| pypi | praisonai | <4.6.37 |
4.6.37 |
Affected products
- MervinPraison PraisonAI
Classification
- Weakness
-
- CWE-470 Use of Externally-Controlled Input to Select Classes or Code
References
-
github.com
/MervinPraison/PraisonAI/security/advisories/GHSA-gmjg-hv98-qggq
exploit, web, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-44339
advisory
-
github.com
/MervinPraison/PraisonAI
package
-
pypi.org
/project/praisonai
package
-
github.com
/advisories/GHSA-gmjg-hv98-qggq
advisory
-
pypi.org
/project/praisonaiagents
package
Sources
- CVE List CVE-2026-44339
- GitHub Advisory GHSA-gmjg-hv98-qggq
- NVD CVE-2026-44339
- OSV PYSEC-2026-2915
- OSV PYSEC-2026-2948
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.