PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
CVE-2026-47392 · GHSA-4mr5-g6f9-cfrh · published 2026-05-29
- Severity
- Critical
- CVSS score
- 9.9
- Chance of exploitation (EPSS)
- 0.88%
- Fixed in
- 1.6.40
- Exploitation Public proof of concept
- Automatable No
- Technical impact Total
- CISA SSVC
An attacker who can influence agent input (via prompt injection, malicious documents, or direct code submission) can: Execute arbitrary commands on the host system Read/write any file accessible to the process Exfiltrate environment variables, API keys, and credentials Pivot to internal networks Install persistent backdoors ---
Upgrade praisonaiagents to 1.6.40 or later, and praisonai to 4.6.40 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
Add self to blockedattrs:
Denylist-based Python sandboxes are fundamentally insecure. Each patch introduces a new bypass opportunity. Consider: Using isolated-vm (Node.js) or WebAssembly-based isolation Using OS-level sandboxing (seccomp, namespaces, gVisor) Removing in-process code execution entirely in favor of containerized execution
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonaiagents | PyPI | <= 1.6.39 | 1.6.40 |
| praisonai | PyPI | <= 4.6.39 | 4.6.40 |
1 registered MCP server installs an affected version today, by the dependency versions a fresh install resolves.
- io.github.MervinPraison/praisonaipraisonai@2.3.42
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
- CriticalPraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secretspraisonaiagents
- CriticalPraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Callspraisonai
- CriticalPraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generationpraisonai
- CriticalPraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92praisonai
- CriticalPraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validationpraisonai
- CriticalPraisonAI: Unauthenticated RCE via Jobs API + Approval Bypasspraisonaiagents, praisonai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.