CVE-2026-47394
PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate
Description
PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` ("fix(security): harden MCP rules path handling…") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params["arguments"]` with no enforcement against the tool's declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix.
INFO
Published Date :
July 21, 2026, 4:17 p.m.
Last Modified :
Oct. 24, 2026, 7:10 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Update PraisonAI to version 4.6.40 or later.
- Verify all handlers and the dispatcher are secured.
- Apply vendor patches promptly.
- Monitor for further security advisories.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-47394.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-47394 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-2026-47394
weaknesses.
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-2026-47394 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-47394 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 Translated by [email protected]
Oct. 24, 2026
Action Type Old Value New Value Added Translation Title: PraisonAI de MervinPraison, Description: PraisonAI es un sistema de equipos multiagente. Antes de la versión 4.6.40, la corrección para GHSA-9mqq-jqxf-grvw / CVE-2026-44336 está incompleta. La descripción del aviso original nombró cuatro manejadores vulnerables en “mcp_server/adapters/cli_tools.py”. El commit “68cc9427” (’fix(security): harden MCP rules path handling...’) añadió una función auxiliar “_resolve_rule_path()” y la aplicó a “rules.create”, “rules.show”, y “rules.delete”. “workflow.show” se dejó sin cambios. Dos manejadores adyacentes en el mismo archivo tienen el mismo patrón, “workflow.validate” y “deploy.validate”. Ninguno de los dos fue mencionado en el aviso original. Ambos permanecieron sin cambios. El aviso original también identificó el despachador (“server.py:281-298”) como una causa raíz. Acepta “kwargs” no validados de “params[’arguments’]” sin aplicación de restricciones contra el “input_schema” declarado de la herramienta. Ese código está sin cambios antes de la versión 4.6.40. Una única llamada “tools/call” de MCP no autenticada a “praisonai.workflow.show” devuelve el contenido de cualquier archivo que el usuario del host pueda leer: “/etc/p4ssd”, “~/.ssh/id_rsa”, “~/.aws/credentials”, o cualquier archivo “.env” del proyecto. La versión 4.6.40 contiene una corrección actualizada. -
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-9cr9-25q5-8prj Added SSVC {'id': 'CVE-2026-47394', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'yes'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-07-21T18:00:46.506651Z'} -
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'}]}] Added Description PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` ("fix(security): harden MCP rules path handling…") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pattern, `workflow.validate` and `deploy.validate`. Neither was mentioned in the original advisory. Both remained unchanged. The original advisory also identified the dispatcher (`server.py:281-298`) as a root cause. It accepts unvalidated `**kwargs` from `params["arguments"]` with no enforcement against the tool's declared `input_schema`. That code is unchanged prior to version 4.6.40. A single unauthenticated MCP `tools/call` to `praisonai.workflow.show` returns the contents of any file the host user can read: `/etc/passwd`, `~/.ssh/id_rsa`, `~/.aws/credentials`, or any project `.env`. Version 4.6.40 contains an updated fix. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CWE CWE-22 Added CWE CWE-200 Added CWE CWE-862 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-9cr9-25q5-8prj