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

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2026-34938— PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code

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 1.5.90之前版本存在安全漏洞，该漏洞源于execute_code函数的三层沙箱可被完全绕过，通过传递具有重写startswith方法的str子类，可能导致在主机上执行任意操作系统命令。

CVSS 10.0 · Critical EPSS 1.30% · P68

Possible ATT&CK Techniques 1 AI

T1203 · Exploitation for Client Execution
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-34938

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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: Python Sandbox Escape via str Subclass startswith() Override in execute_code
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
保护机制失效
Source: CVE Program / CVE List V5
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 1.5.90之前版本存在安全漏洞，该漏洞源于execute_code函数的三层沙箱可被完全绕过，通过传递具有重写startswith方法的str子类，可能导致在主机上执行任意操作系统命令。
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)

Shenlong Deep Dive — AI Deep Analysis

10-question deep dive: root cause, exploitation, mitigation, urgency. Read summary free, full version requires login.

Read summary Full analysis (login)

Affected Products

Vendor Product Affected Versions CPE Subscribe
MervinPraison PraisonAI < 1.5.90 -

II. Public POCs for CVE-2026-34938

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-34938

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-34938 (1)

Same Patch Batch · MervinPraison · 2026-04-03 · 10 CVEs total

CVE-2026-34934 9.8 CRITICAL PraisonAI: Second-Order SQL Injection in `get_all_user_threads`
CVE-2026-34935 9.8 CRITICAL PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
CVE-2026-34952 9.1 CRITICAL PraisonAI: Missing Authentication in WebSocket Gateway
CVE-2026-34953 9.1 CRITICAL PraisonAI: Authentication Bypass in OAuthManager.validate_token()
CVE-2026-34955 8.8 HIGH PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox
CVE-2026-34954 8.6 HIGH PraisonAI: SSRF in FileTools.download_file() via Unvalidated URL
CVE-2026-34937 7.8 HIGH PraisonAI: Shell Injection in run_python() via Unescaped $() Substitution
CVE-2026-34936 7.7 HIGH PraisonAI: SSRF via Unvalidated api_base in passthrough() Fallback
CVE-2026-34939 6.5 MEDIUM PraisonAI: ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

IV. Related Vulnerabilities

Same product: PraisonAI
Same vendor: MervinPraison
Same weakness: CWE-693

V. Comments for CVE-2026-34938

No comments yet

Leave a comment