CVE-2026-57145— PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation
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 是一个多智能体（multi-agent）系统。在 4.6.62 版本之前， 中的实现将 LLM（大语言模型）控制的 参数直接传递给 函数进行读写操作，但并未实施路径遍历（path traversal）的拒绝机制、符号链接（symlink）解析、工作区边界限制或受保护路径的检查。受提示词（prompt）影响的智能体可以通过编辑（edit）和差异对比（diff）行为读取文件，或覆盖该进程可访问的文件，从而泄露机密信息，并可能导致持久化后门或应用程序被篡改。该问题已在 4.6.62 版本中修复。
Possible ATT&CK Techniques 1 AI
T1083 · File and Directory Discovery
Get alerts for future matching vulnerabilities
Log in to subscribe
I. Basic Information for CVE-2026-57145
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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 File Read/Write via `multiedit` Tool Without Path Validation
Source: CVE Program / CVE List V5
Vulnerability Description
PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to open for reading and writing without traversal rejection, symlink resolution, a workspace boundary, or protected-path checks. Prompt-influenced agents can read files through edit and diff behavior or overwrite files accessible to the process, exposing secrets and enabling persistence or application tampering. This issue is fixed in 4.6.62.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
对路径名的限制不恰当(路径遍历)
Source: CVE Program / CVE List V5
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| MervinPraison | PraisonAI | < 4.6.62 | - |
|
II. Public POCs for CVE-2026-57145
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POC
Premium
No public POC found.
Login to generate AI POCIII. Intelligence Information for CVE-2026-57145
请登录查看更多情报信息。
Vendor Advisories for CVE-2026-57145 (1)
Vendor Pages for CVE-2026-57145 (1)
-
🔗 Release PraisonAI v4.6.62 · MervinPraison/PraisonAI · GitHub x_refsource_MISC
Same Patch Batch · MervinPraison · 2026-09-14 · 16 CVEs total
| CVE-2026-57123 | 9.8 CRITICAL | PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation |
| CVE-2026-57124 | 9.8 CRITICAL | PraisonAI UI MCP connect endpoint allows unauthenticated local command execution |
| CVE-2026-57125 | 9.8 CRITICAL | PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass |
| CVE-2026-57127 | 9.8 CRITICAL | praisonai: recipe serve auth middleware silently disables itself when no secret is set |
| CVE-2026-57131 | 9.8 CRITICAL | praisonai: Jobs API exposes agent-execution endpoints with no authentication |
| CVE-2026-57122 | 8.6 HIGH | PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing |
| CVE-2026-57126 | 8.5 HIGH | praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS |
| CVE-2026-57132 | 8.2 HIGH | PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables auth |
| CVE-2026-57130 | 8.1 HIGH | PraisonAI: IMAP Command Injection via Unsanitized Email Search Parameters |
| CVE-2026-57119 | 7.5 HIGH | PraisonAI: Unauthenticated Local File Inclusion via agent_file path in the Jobs API |
| CVE-2026-57129 | 7.5 HIGH | PraisonAI: Arbitrary File Read via `@file:` Mention Path Traversal |
| CVE-2026-56839 | 7.3 HIGH | PraisonAI Code agent tools fail open without a workspace boundary |
| CVE-2026-57115 | 6.5 MEDIUM | PraisonAI: SpiderTools redirect-target SSRF protection bypass |
| CVE-2026-57120 | 6.5 MEDIUM | PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every bl |
| CVE-2026-57128 | 4.3 MEDIUM | PraisonAI: Unauthenticated Event Injection via SSE `/publish` Endpoint |
IV. Related Vulnerabilities
Same product: PraisonAI
-
CVE-2026-57132
PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable -
CVE-2026-57131
praisonai: Jobs API exposes agent-execution endpoints with n -
CVE-2026-57124
PraisonAI UI MCP connect endpoint allows unauthenticated loc -
CVE-2026-57122
PraisonAI: Webhook signature verification skipped (fail-open -
CVE-2026-57127
praisonai: recipe serve auth middleware silently disables it
Same vendor: MervinPraison
-
CVE-2026-57132
PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable -
CVE-2026-57131
praisonai: Jobs API exposes agent-execution endpoints with n -
CVE-2026-57124
PraisonAI UI MCP connect endpoint allows unauthenticated loc -
CVE-2026-57122
PraisonAI: Webhook signature verification skipped (fail-open -
CVE-2026-57127
praisonai: recipe serve auth middleware silently disables it
Same weakness: CWE-22
-
CVE-2026-54150
next-video: Unauthenticated arbitrary file read via /api/vid -
CVE-2026-55846
Allure: Path Traversal in Allure Report HTTP Server Allows A -
CVE-2026-56839
PraisonAI Code agent tools fail open without a workspace bou -
CVE-2026-57119
PraisonAI: Unauthenticated Local File Inclusion via agent_fi -
CVE-2026-57129
PraisonAI: Arbitrary File Read via `@file:` Mention Path Tra
V. Comments for CVE-2026-57145
No comments yet