CVE-2026-44334— PraisonAI: Unauthenticated RCE via `tool_override.py`
Quick assessment
Affected
MervinPraison PraisonAI
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
PraisonAI是Mervin Praison个人开发者的一个低代码多智能体协作框架。 PraisonAI 4.5.139至4.6.32之前版本存在代码注入漏洞，该漏洞源于tool_override.py中未对工具自动导入进行防护，可能导致未经身份验证的攻击者通过POST /v1/recipes/run触发远程代码执行。
Possible ATT&CK Techniques 2 AI
T1059 · Command and Scripting Interpreter T1203 · Exploitation for Client ExecutionAffected Version Matrix 1
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| MervinPraison | PraisonAI | >= 4.5.139, < 4.6.32 |
affected |
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-44334
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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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: Unauthenticated RCE via `tool_override.py`
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI is a multi-agent teams system. From version 4.5.139 to before version 4.6.32, CVE-2026-40287's fix gated tools.py auto-import behind PRAISONAI_ALLOW_LOCAL_TOOLS=true in two files (tool_resolver.py, api/call.py). A third import sink in praisonai/templates/tool_override.py was missed and remains unguarded. It is reached by the recipe runner on every recipe execution and is remotely triggerable through POST /v1/recipes/run with a recipe value pointing at any local absolute path or any GitHub repo (because SecurityConfig.allow_any_github defaults to True). The attacker drops a tools.py next to TEMPLATE.yaml; the server exec_module()s it. No auth required by default, no environment opt-in required. This issue has been patched in version 4.6.32.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5
Vulnerability Title
PraisonAI 代码注入漏洞
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 4.5.139至4.6.32之前版本存在代码注入漏洞，该漏洞源于tool_override.py中未对工具自动导入进行防护，可能导致未经身份验证的攻击者通过POST /v1/recipes/run触发远程代码执行。
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
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| MervinPraison | PraisonAI | >= 4.5.139, < 4.6.32 | - |
|
II. Public POCs for CVE-2026-44334
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-44334
请登录查看更多情报信息。
Vendor Advisories for CVE-2026-44334 (1)
Same Patch Batch · MervinPraison · 2026-05-08 · 9 CVEs total
| CVE-2026-41497 | 9.8 CRITICAL | Incomplete fix for CVE-2026-34935: Command Injection in MervinPraison/PraisonAI |
| CVE-2026-44339 | 8.6 HIGH | PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__m |
| CVE-2026-41496 | 8.1 HIGH | PraisonAI: SQL Injection via unvalidated `table_prefix` in 9 conversation store backends ( |
| CVE-2026-44338 | 7.3 HIGH | PraisonAI ships and generates a legacy API server with authentication disabled by default, |
| CVE-2026-44337 | 6.3 MEDIUM | PraisonAI knowledge-store backends interpolate unvalidated collection names into SQL and C |
| CVE-2026-44340 | PraisonAI: Symlink-extraction bypass of `_safe_extractall` writes outside `dest_dir` | |
| CVE-2026-44335 | SSRF bypass in PraisonAI | |
| CVE-2026-44336 | PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection |
IV. Related Vulnerabilities
Same product: PraisonAI
-
CVE-2026-62176
PraisonAI: Code Injection via f-string Interpolation in Depl -
CVE-2026-57147
praisonai-platform: default JWT signing secret 'dev-secret-c -
CVE-2026-57148
praisonai-platform 0.1.4 still boots on the hardcoded JWT se -
CVE-2026-57140
PraisonAI AgentOS exposes unauthenticated agent listing and -
CVE-2026-57139
PraisonAI MCPServer exposes unauthenticated HTTP tools/call
Same vendor: MervinPraison
-
CVE-2026-62176
PraisonAI: Code Injection via f-string Interpolation in Depl -
CVE-2026-62179
PraisonAI: Platform members can delete owner issue dependenc -
CVE-2026-57147
praisonai-platform: default JWT signing secret 'dev-secret-c -
CVE-2026-57148
praisonai-platform 0.1.4 still boots on the hardcoded JWT se -
CVE-2026-57140
PraisonAI AgentOS exposes unauthenticated agent listing and
Same weakness: CWE-94
-
CVE-2026-108259
Tina: Code injection via unescaped Git branch name in genera -
CVE-2026-104082
SmarterMail < Build 9777 SysAdmin Remote Code Execution via -
CVE-2026-107806
Nginx UI: Authenticated Remote Code Execution via Backup Res -
CVE-2026-107732
SumatraPDF: Markup/command-link injection into UI notificati -
CVE-2026-11888
Security vulnerabilities have been found in IBM Verify Ident
V. Comments for CVE-2026-44334
No comments yet