CVE-2026-44336— PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection
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 4.6.34之前版本存在输入验证错误漏洞，该漏洞源于MCP服务器中文件处理工具未对路径进行包含检查，可能导致攻击者通过路径遍历写入任意文件，并升级为任意代码执行。
Possible ATT&CK Techniques 3 AI
T1055 · Process Injection T1204 · User Execution T1059 · Command and Scripting InterpreterAffected Version Matrix 1
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| MervinPraison | PraisonAI | < 4.6.34 |
affected |
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-44336
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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 MCP `tools/call` path-traversal and RCE via Python `.pth` injection
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params["arguments"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name="../../<some-path>" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Source: CVE Program / CVE List V5
Vulnerability Type
输入验证不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
PraisonAI 输入验证错误漏洞
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 4.6.34之前版本存在输入验证错误漏洞，该漏洞源于MCP服务器中文件处理工具未对路径进行包含检查，可能导致攻击者通过路径遍历写入任意文件，并升级为任意代码执行。
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 | < 4.6.34 | - |
|
II. Public POCs for CVE-2026-44336
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-44336
请登录查看更多情报信息。
Vendor Advisories for CVE-2026-44336 (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-2026-44334 | 8.4 HIGH | PraisonAI: Unauthenticated RCE via `tool_override.py` |
| 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 |
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-20
-
CVE-2026-107825
OWASP Coraza WAF: ProcessURI silently drops QUERY_STRING and -
CVE-2026-48484
pyLoad: Lack of Input Size Validation Leads to Denial of Ser -
CVE-2026-103413
Apache Camel Karavan: unvalidated Kubernetes resources appli -
CVE-2026-107734
SumatraPDF: SyncTeX Argument Injection in Inverse Search Ena -
CVE-2026-107726
Hazelcast: Arbitrary member memory access by low-privileged
V. Comments for CVE-2026-44336
No comments yet