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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-40149— PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls

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 4.5.128之前版本存在安全漏洞，该漏洞源于/api/approval/allow-list端点默认允许未经身份验证修改工具批准白名单，可能导致攻击者绕过人工审批机制，自动批准危险工具调用。

CVSS 7.9 · High EPSS 0.16% · P5

Possible ATT&CK Techniques 1 AI

T1190 · Exploit Public-Facing Application
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-40149

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g., shell_exec, file_write) to the allowlist, an attacker can cause the ExecApprovalManager to auto-approve all future agent invocations of those tools, bypassing the human-in-the-loop safety mechanism that the approval system is specifically designed to enforce. This vulnerability is fixed in 4.5.128.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:C/C:L/I:H/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
对通用异常声明Catch语句
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 4.5.128之前版本存在安全漏洞，该漏洞源于/api/approval/allow-list端点默认允许未经身份验证修改工具批准白名单，可能导致攻击者绕过人工审批机制，自动批准危险工具调用。
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 < 4.5.128 -

II. Public POCs for CVE-2026-40149

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-40149

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-40149 (1)

Same Patch Batch · MervinPraison · 2026-04-09 · 15 CVEs total

CVE-2026-40088 9.7 CRITICAL Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
CVE-2026-40154 9.3 CRITICAL PraisonAI Affected by Untrusted Remote Template Code Execution
CVE-2026-40113 8.4 HIGH PraisonAI has an Argument Injection into Cloud Run Environment Variables via Unsanitized C
CVE-2026-40150 7.7 HIGH PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool
CVE-2026-40116 7.5 HIGH PraisonAI's Unauthenticated WebSocket Endpoint Proxies to Paid OpenAI Realtime API Without
CVE-2026-40153 7.4 HIGH PraisonAIAgents Affected by Environment Variable Secret Exfiltration via os.path.expandvar
CVE-2026-40114 7.2 HIGH PraisonAI has Server-Side Request Forgery via Unvalidated webhook_url in Jobs API
CVE-2026-40148 6.5 MEDIUM PraisonAI Affected by Decompression Bomb DoS via Recipe Bundle Extraction Without Size Lim
CVE-2026-40115 6.2 MEDIUM PraisonAI has an Unrestricted Upload Size in WSGI Recipe Registry Server Enables Memory Ex
CVE-2026-40117 6.2 MEDIUM PraisonAIAgents Affected by Arbitrary File Read via read_skill_file Missing Workspace Boun
CVE-2026-40112 5.4 MEDIUM PraisonAI has Stored XSS via Unsanitized Agent Output in HTML Rendering (nh3 Not a Require
CVE-2026-40151 5.3 MEDIUM PraisonAI Affected by Unauthenticated Information Disclosure of Agent Instructions via /ap
CVE-2026-40152 5.3 MEDIUM PraisonAIAgents has a Path Traversal via Unvalidated Glob Pattern in list_files Bypasses W
CVE-2026-40111 PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memor

IV. Related Vulnerabilities

Same product: PraisonAI
Same vendor: MervinPraison
Same weakness: CWE-396

V. Comments for CVE-2026-40149

No comments yet

Leave a comment