Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1020 CNY

100%
Buy Us a Coffee

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

CVSS 8.6 · High EPSS 0.09% · P25

Possible ATT&CK Techniques 1AI

T1059 · Command and Scripting Interpreter

Affected Version Matrix 2

VendorProductVersion RangeStatus
MervinPraisonPraisonAIpraisonaiagents < 1.6.37affected
praisonai < 4.6.37affected
Get alerts for future matching vulnerabilitiesLog in to subscribe

I. Basic Information for CVE-2026-44339

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables execute
Source: NVD (National Vulnerability Database)
Vulnerability 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.
Source: NVD (National Vulnerability Database)
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:L
Source: NVD (National Vulnerability Database)
Vulnerability Type
使用外部可控制的输入来选择类或代码(不安全的反射)
Source: NVD (National Vulnerability Database)
Vulnerability Title
PraisonAI 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
PraisonAI是Mervin Praison个人开发者的一个低代码多智能体协作框架。 PraisonAI 4.6.37之前版本和PraisonAIagents 1.6.37之前版本存在安全漏洞，该漏洞源于未声明的工具名称解析问题，可能导致攻击者调用未声明的应用程序可调用对象。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

VendorProductAffected VersionsCPESubscribe
MervinPraisonPraisonAI praisonaiagents < 1.6.37 -

II. Public POCs for CVE-2026-44339

#POC DescriptionSource LinkShenlong Link
AI-Generated POCPremium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-44339

请登录查看更多情报信息。
Advisory · 1

Same Patch Batch · MervinPraison · 2026-05-08 · 9 CVEs total

CVE-2026-414979.8 CRITICALIncomplete fix for CVE-2026-34935: Command Injection in MervinPraison/PraisonAI
CVE-2026-443348.4 HIGHPraisonAI: Unauthenticated RCE via `tool_override.py`
CVE-2026-414968.1 HIGHPraisonAI: SQL Injection via unvalidated `table_prefix` in 9 conversation store backends (
CVE-2026-443387.3 HIGHPraisonAI ships and generates a legacy API server with authentication disabled by default,
CVE-2026-443376.3 MEDIUMPraisonAI knowledge-store backends interpolate unvalidated collection names into SQL and C
CVE-2026-44340PraisonAI: Symlink-extraction bypass of `_safe_extractall` writes outside `dest_dir`
CVE-2026-44335SSRF bypass in PraisonAI
CVE-2026-44336PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection

IV. Related Vulnerabilities

Same product: PraisonAI
Same vendor: MervinPraison
Same weakness: CWE-470

V. Comments for CVE-2026-44339

No comments yet

Leave a comment