CVE-2026-61447— PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
Quick assessment
Affected
MervinPraison PraisonAI
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.
Mervin Praison PraisonAI是Mervin Praison个人开发者开源的一个低代码多智能体协作框架。 Mervin Praison PraisonAI 1.6.78之前版本存在代码注入漏洞，该漏洞源于CodeAgent._execute_python()中执行LLM生成的Python代码时没有AST验证、导入限制或沙箱强制执行，攻击者可通过提示注入影响LLM输出，从而窃取所有环境机密并在主机系统上执行任意代码。
Public Exploits 1
ExploitDB · 1
EDB-52639 [remote]
Possible ATT&CK Techniques 3 AI
T1005 · Data from Local System T1057 · Process Discovery T1059 · Command and Scripting InterpreterAffected Version Matrix 2
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| MervinPraison | PraisonAI | < 1.6.78 |
affected |
1.6.78 |
unaffected |
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-61447
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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 before 1.6.78 Remote Code Execution via CodeAgent
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.
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
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5
Vulnerability Title
Mervin Praison PraisonAI 代码注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Mervin Praison PraisonAI是Mervin Praison个人开发者开源的一个低代码多智能体协作框架。 Mervin Praison PraisonAI 1.6.78之前版本存在代码注入漏洞，该漏洞源于CodeAgent._execute_python()中执行LLM生成的Python代码时没有AST验证、导入限制或沙箱强制执行，攻击者可通过提示注入影响LLM输出，从而窃取所有环境机密并在主机系统上执行任意代码。
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 | 0 ~ 1.6.78 | - |
|
II. Public POCs for CVE-2026-61447
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
Qwen3.6-35B-A3B
· 6176 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month
III. Intelligence Information for CVE-2026-61447
请登录查看更多情报信息。
Vendor Advisories for CVE-2026-61447 (1)
Other References for CVE-2026-61447 (1)
-
🔗 Page Not Found | VulnCheck third-party-advisory
Same Patch Batch · MervinPraison · 2026-07-11 · 9 CVEs total
| CVE-2026-61445 | 9.9 CRITICAL | PraisonAI before 4.6.78 Arbitrary File Write and Command Execution |
| CVE-2026-60090 | 9.8 CRITICAL | PraisonAI before 4.6.78 SQL/CQL Injection via vector dimension |
| CVE-2026-61426 | 8.6 HIGH | PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults |
| CVE-2026-61429 | 8.5 HIGH | PraisonAI before 1.6.78 SSRF via Crawl4AI Chromium backend |
| CVE-2026-61439 | 7.5 HIGH | PraisonAI before 4.6.78 Prompt Injection Defense Bypass |
| CVE-2026-61428 | 7.3 HIGH | PraisonAI AgentMail before 4.6.78 Message Injection via Webhook |
| CVE-2026-61442 | 7.1 HIGH | PraisonAI Platform before 0.1.9 Authorization Bypass via PATCH |
| CVE-2026-60088 | 5.5 MEDIUM | PraisonAI before 4.6.78 Path Traversal via Custom Commands |
IV. Related Vulnerabilities
Same product: PraisonAI
-
CVE-2026-57118
PraisonAI AgentTeam.launch exposes unauthenticated remote ag -
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
Same vendor: MervinPraison
-
CVE-2026-57118
PraisonAI AgentTeam.launch exposes unauthenticated remote ag -
CVE-2026-57143
PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / s -
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
Same weakness: CWE-94
-
CVE-2026-106621
ColdFusion | Improper Control of Generation of Code ('Code I -
CVE-2026-105903
ColdFusion | Improper Control of Generation of Code ('Code I -
CVE-2026-63146
Omnispace Agora Project < 26.10.0 PHP Code Injection via con -
CVE-2026-102870
ASP.NET Core Remote Code Execution Vulnerability -
CVE-2026-96220
Windows Assigned Access Elevation of Privilege Vulnerability
V. Comments for CVE-2026-61447
No comments yet