9.9
CRITICAL CVSS 3.1
CVE-2026-47392
PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)
Description

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix.

INFO

Published Date :

July 21, 2026, 4:17 p.m.

Last Modified :

July 21, 2026, 6:59 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-47392 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

No affected product recoded yet

CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 134c704f-9b21-4f2e-91b3-4a467353bcc0
CVSS 3.1 CRITICAL [email protected]
Solution
Update PraisonAI and praisonaiagents to the latest versions to fix arbitrary OS command execution.
  • Update PraisonAI to version 4.6.40 or later.
  • Update praisonaiagents to version 1.6.40 or later.
References to Advisories, Solutions, and Tools
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-47392 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-47392 weaknesses.

CAPEC-3: Using Leading 'Ghost' Character Sequences to Bypass Input Filters Using Leading 'Ghost' Character Sequences to Bypass Input Filters CAPEC-6: Argument Injection Argument Injection CAPEC-15: Command Delimiters Command Delimiters CAPEC-43: Exploiting Multiple Input Interpretation Layers Exploiting Multiple Input Interpretation Layers CAPEC-71: Using Unicode Encoding to Bypass Validation Logic Using Unicode Encoding to Bypass Validation Logic CAPEC-73: User-Controlled Filename User-Controlled Filename CAPEC-85: AJAX Footprinting AJAX Footprinting CAPEC-120: Double Encoding Double Encoding CAPEC-182: Flash Injection Flash Injection CAPEC-1: Accessing Functionality Not Properly Constrained by ACLs Accessing Functionality Not Properly Constrained by ACLs CAPEC-17: Using Malicious Files Using Malicious Files CAPEC-20: Encryption Brute Forcing Encryption Brute Forcing CAPEC-22: Exploiting Trust in Client Exploiting Trust in Client CAPEC-36: Using Unpublished Interfaces or Functionality Using Unpublished Interfaces or Functionality CAPEC-51: Poison Web Service Registry Poison Web Service Registry CAPEC-57: Utilizing REST's Trust in the System Resource to Obtain Sensitive Data Utilizing REST's Trust in the System Resource to Obtain Sensitive Data CAPEC-59: Session Credential Falsification through Prediction Session Credential Falsification through Prediction CAPEC-65: Sniff Application Code Sniff Application Code CAPEC-74: Manipulating State Manipulating State CAPEC-87: Forceful Browsing Forceful Browsing CAPEC-107: Cross Site Tracing Cross Site Tracing CAPEC-127: Directory Indexing Directory Indexing CAPEC-237: Escaping a Sandbox by Calling Code in Another Language Escaping a Sandbox by Calling Code in Another Language CAPEC-477: Signature Spoofing by Mixing Signed and Unsigned Content Signature Spoofing by Mixing Signed and Unsigned Content CAPEC-480: Escaping Virtualization Escaping Virtualization CAPEC-668: Key Negotiation of Bluetooth Attack (KNOB) Key Negotiation of Bluetooth Attack (KNOB)

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-47392 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-47392 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Jul. 21, 2026

    Action Type Old Value New Value
    Added Reference https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh
    Added SSVC {'id': 'CVE-2026-47392', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-07-21T16:39:00.607801Z'}
  • New CVE Received by [email protected]

    Jul. 21, 2026

    Action Type Old Value New Value
    Added Affected [{'vendor': 'MervinPraison', 'product': 'PraisonAI', 'versions': [{'status': 'affected', 'version': '< 4.6.40'}]}, {'vendor': 'MervinPraison', 'product': '< 1.6.40', 'versions': [{'status': 'affected', 'version': 'praisonaiagents'}]}]
    Added Description PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. This is a novel bypass that survives all patches for CVE-2026-39888 (frame traversal), CVE-2026-34938 (str subclass), and CVE-2026-40158 (`type.__getattribute__` trampoline). PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain an updated fix.
    Added CVSS V3.1 AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
    Added CWE CWE-693
    Added CWE CWE-184
    Added Reference https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6
    Added Reference https://github.com/MervinPraison/PraisonAI/pull/1684
    Added Reference https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4mr5-g6f9-cfrh
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.