Read the docs
TI-2026-32306 Aliases CVE-2026-44339GHSA-gmjg-hv98-qggq

PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute

Priority HIGH 76CWE-470Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Impact type
—
Confidentiality · integrity · availability
Low · High · Low
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub.

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00363 30th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Fixed praisonaiagents (PyPI): 1.6.37PraisonAI (PyPI): 4.6.37

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
Yes
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
MervinPraisonPraisonAIpraisonaiagents < 1.6.37; praisonai < 4.6.37—No fix listedCNA
—praisonaiagents (PyPI)before 1.6.371.6.37Patch availableGHSA-gmjg-hv98-qggq
—PraisonAI (PyPI)before 4.6.374.6.37Patch availableGHSA-gmjg-hv98-qggq
  • PraisonAI VendorMervinPraison Affected praisonaiagents < 1.6.37; praisonai < 4.6.37 Fixed in — No fix listed CNA
  • praisonaiagents (PyPI) Vendor— Affected before 1.6.37 Fixed in 1.6.37 Patch available GHSA-gmjg-hv98-qggq
  • PraisonAI (PyPI) Vendor— Affected before 4.6.37 Fixed in 4.6.37 Patch available GHSA-gmjg-hv98-qggq

CPE configurations NVD · 2

CPEVersionsRoleVendor
cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*before 4.6.37VulnerableMervinPraison
cpe:2.3:a:praison:praisonaiagents:*:*:*:*:*:python:*:*before 1.6.37VulnerableMervinPraison
  • cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:* Versions before 4.6.37 Vulnerable ·MervinPraison
  • cpe:2.3:a:praison:praisonaiagents:*:*:*:*:*:python:*:* Versions before 1.6.37 Vulnerable ·MervinPraison

Remediation

  • Fix · GHSA-gmjg-hv98-qggq praisonaiagents (PyPI) Fixed in 1.6.37 Advisory →
  • Fix · GHSA-gmjg-hv98-qggq PraisonAI (PyPI) Fixed in 4.6.37 Advisory →

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-44339
  2. 2026-10-03 Alias added: GHSA-gmjg-hv98-qggq

References

Exploit 1

Advisory 1

Other 1

  • TI-2026-30083 Incomplete fix for CVE-2026-34935: Command Injection in MervinPraison/PraisonAI CVSS 3.1CRITICAL 9.8
  • TI-2026-29070 PraisonAI: Critical RCE via `type: job` workflow YAML CVSS 3.1CRITICAL 9.8
  • TI-2026-28940 PraisonAI has Server-Side Request Forgery via Unvalidated webhook_url in Jobs API CVSS 3.1CRITICAL 10.0
  • TI-2026-28768 PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading CVSS 3.1CRITICAL 9.8
  • TI-2026-27159 PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command() CVSS 3.1CRITICAL 9.8
  • TI-2026-27158 PraisonAI: Second-Order SQL Injection in `get_all_user_threads` CVSS 3.1CRITICAL 9.8
See all 42 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences