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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-56075— PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

Quick assessment

Affected
PraisonAI 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.

PraisonAI PraisonAI是PraisonAI公司的一款整合人工智能代理的服务器中间件软件。 PraisonAI 4.5.128之前版本存在授权问题漏洞，该漏洞源于UI模块将审核模式硬编码为自动，可能绕过管理员配置和命令清理黑名单，可能导致经过身份验证的攻击者通过subprocess.run执行任意Shell命令。

CVSS 8.8 · High EPSS 0.71% · P52

Possible ATT&CK Techniques 1 AI

T1059 · Command and Scripting Interpreter

Affected Version Matrix 2

VendorProduct Version RangeStatus
PraisonAI PraisonAI < 4.5.128 affected
4.5.128 unaffected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-56075

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
授权机制不正确
Source: CVE Program / CVE List V5
Vulnerability Title
PraisonAI 授权问题漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
PraisonAI PraisonAI是PraisonAI公司的一款整合人工智能代理的服务器中间件软件。 PraisonAI 4.5.128之前版本存在授权问题漏洞，该漏洞源于UI模块将审核模式硬编码为自动，可能绕过管理员配置和命令清理黑名单，可能导致经过身份验证的攻击者通过subprocess.run执行任意Shell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)

Affected Products

Vendor Product Affected Versions CPE Subscribe
PraisonAI PraisonAI 0 ~ 4.5.128 -

II. Public POCs for CVE-2026-56075

# POC Description Source Link Shenlong Link
AI-Generated POC Verified env Premium
Qwen3.6-35B-A3B · 8579 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-2026-56075

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-56075 (2)

Same Patch Batch · PraisonAI · 2026-06-18 · 5 CVEs total

CVE-2026-56078 8.8 HIGH PraisonAI - Arbitrary File Read and Write via Path Traversal in MultiAgentMonitor
CVE-2026-56076 8.1 HIGH PraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentic
CVE-2026-56077 6.5 MEDIUM PraisonAI - Information Disclosure via Shared MultiAgentLedger State
CVE-2026-56074 5.5 MEDIUM PraisonAI - Tool Approval Cache Bypass via Coarse-Grained Caching

IV. Related Vulnerabilities

Same product: PraisonAI
Same vendor: PraisonAI
Same weakness: CWE-863

V. Comments for CVE-2026-56075

No comments yet

Leave a comment