PT-2026-61778 · Pypi · Praisonai

CVE-2026-57124 · Publicado 2026-06-18 · Atualizado 2026-07-23

OSV

CVSS v3.1

9.8

Crítica

Vetor base

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands

Summary

PraisonAI v4.6.48 exposes the PraisonAIUI MCP client management API through the default UI host apps without authentication. A remote unauthenticated client can send POST /api/mcp/connect with a command and args field. The endpoint passes those values into the MCP stdio client, which starts the attacker-selected local process as the PraisonAI UI service user.

The issue is reachable through PraisonAI's hosted UI integration (praisonai ui, praisonai ui agents, praisonai claw, and any app using praisonai.integration.host app.create host app() / build host app()). praisonai ui and related Typer UI commands bind to 0.0.0.0 by default.

Affected Versions

Confirmed affected:

• praisonai v4.6.48
• Commit tested: d5f1114aaf1a2e9f121a6e66b929149ca2201f1d
• Tag tested: v4.6.48
• Pinned UI dependency: aiui==0.3.121 from src/praisonai/uv.lock

Likely affected:

• Any PraisonAI release that exposes aiui / praisonaiui create app() through the PraisonAI UI host apps without authentication and includes the mcp dependency. I only confirmed the latest release during this audit.

Severity

Reasoning:

• AV: the vulnerable endpoint is an HTTP API route.
• AC: a single POST request is sufficient.
• PR: default UI host apps do not require credentials unless opt-in auth is configured.
• UI: no victim interaction is needed after the server is running.
• S: code executes in the PraisonAI UI server process context.
• C/I/A: arbitrary local command execution permits secret exfiltration, file tampering, and service disruption.

Root Cause

PraisonAI depends on MCP by default and exposes PraisonAIUI via optional UI extras:

• src/praisonai/pyproject.toml:11 includes base dependencies.
• src/praisonai/pyproject.toml:19 includes mcp>=1.20.0.
• src/praisonai/pyproject.toml:25 defines the ui extra with aiui>=0.3.121,<0.4.
• src/praisonai/pyproject.toml:197 defines the claw extra with aiui[all]>=0.3.121,<0.4.

PraisonAI's UI commands bind externally by default and launch aiui run:

• src/praisonai/praisonai/cli/commands/ui.py:114 sets host="0.0.0.0" for praisonai ui.
• src/praisonai/praisonai/cli/commands/ui.py:163 passes that host to aiui run.
• src/praisonai/praisonai/cli/commands/ui.py:186, :204, and :222 also default subcommands to 0.0.0.0.
• src/praisonai/praisonai/cli/commands/claw.py:41 defines the full dashboard command.
• src/praisonai/praisonai/cli/commands/claw.py:93 launches aiui run with the selected host.

PraisonAI's default apps create the PraisonAIUI Starlette app without forcing authentication:

• src/praisonai/praisonai/ui chat/default app.py:18 calls configure host(...).
• src/praisonai/praisonai/ui chat/default app.py:142 exports app = create host app().
• src/praisonai/praisonai/claw/default app.py:63 calls configure host(...).
• src/praisonai/praisonai/claw/default app.py:128 exports app = create host app().
• src/praisonai/praisonai/integration/host app.py:174 imports praisonaiui.server.create app.
• src/praisonai/praisonai/integration/host app.py:180 returns create app().

In aiui==0.3.121, the exposed server registers the MCP routes and auth is opt-in:

• praisonaiui/server.py:1483 defines api mcp connect.
• praisonaiui/server.py:1488 reads attacker-controlled JSON.
• praisonaiui/server.py:1491 accepts either command or url.
• praisonaiui/server.py:1496 calls connect mcp server(body).
• praisonaiui/server.py:2516 defines create app(..., require auth=False, ...).
• praisonaiui/server.py:2550 adds AuthEnforcementMiddleware, but it only enforces auth when AUTH ENFORCE=true.
• praisonaiui/server.py:2769 registers /api/mcp/servers.
• praisonaiui/server.py:2770 registers /api/mcp/connect.

The MCP feature converts the request body into a local process launch:

• praisonaiui/features/mcp.py:325 defines connect server(self, server config).
• praisonaiui/features/mcp.py:330 chooses stdio transport when command is present.
• praisonaiui/features/mcp.py:332 constructs StdioMCPClient(command=server config["command"], args=server config.get("args", [])).
• praisonaiui/features/mcp.py:360 calls client.connect(), which invokes the MCP stdio transport and starts the process.

Minimal PoC

PoC file: poc/praisonai-aiui-mcp-connect-rce.py

The PoC runs the PraisonAI host app in-process, sends the unauthenticated HTTP request, and asks the server to execute /usr/bin/touch /tmp/praisonai host app mcp touch marker.txt. It does not contact an LLM provider and uses no credentials.

Observed output from the tested checkout with aiui==0.3.121 and mcp==1.25.0 available:

[19:19:55] server.py:229 WARNING No auth token provided for Gateway server. Generated temporary token: gw ****650a. For production, set GATEWAY AUTH TOKEN.
[19:19:55] mcp.py:135 ERROR Failed to connect to MCP stdio server: 'tuple' object has no attribute 'initialize'
HTTP STATUS= 200
RESPONSE= {"server":{"name":"poc-stdio-process-0","transport":"stdio","status":"error","tools":[],"last error":"Connection failed"}}
SUCCESS AT ATTEMPT= 0
MARKER EXISTS= True
MARKER PATH= /tmp/praisonai host app mcp touch marker.txt

The MCP handshake fails because aiui==0.3.121 is not compatible with the locked mcp==1.25.0 return shape, but the attacker-selected process is already started. Process startup can race the immediate teardown caused by this version mismatch, so the checked-in PoC retries the same unauthenticated request until /usr/bin/touch wins scheduling and creates the marker. The marker file proves local command execution despite the reported MCP connection error.

Exploit Scenario

An operator runs:

pip install "praisonai[ui]"
praisonai ui

Because praisonai ui binds to 0.0.0.0 by default and the generated app does not require authentication by default, any host that can reach the UI port can send:

POST /api/mcp/connect
Content-Type: application/json

{
 "name": "evil",
 "command": "/usr/bin/touch",
 "args": ["/tmp/pwned-by-ui-mcp"]
}

In a real attack, the command can be replaced with a shell, a credential exfiltration command, a file modification command, or a payload that starts a long-lived process as the PraisonAI UI server user.

Novelty / Non-Duplicate Analysis

Searched sources:

• OSV query for PyPI praisonai: 51 advisories returned.
• OSV query for PyPI aiui: 0 advisories returned.
• OSV query for PyPI praisonaiui: 0 advisories returned.
• GitHub Advisory Database search for exact /api/mcp/connect, api mcp connect, StdioMCPClient, connect mcp server, and praisonaiui.features.mcp.
• NVD API searches for PraisonAI StdioMCPClient, PraisonAI api mcp connect, PraisonAI /api/mcp/connect, PraisonAIUI /api/mcp/connect, and aiui StdioMCPClient: 0 results.
• GitHub issue/PR searches in MervinPraison/PraisonAI for exact endpoint/function/class terms. Only one unrelated PR was returned for /api/mcp/connect; no issue/PR matched api mcp connect, StdioMCPClient, connect mcp server, or praisonaiui.features.mcp.
• Broad web searches for exact endpoint, file, class, and function terms returned no matching public vulnerability report.

Why this is distinct from known PraisonAI advisories:

• Not the excluded praisonai serve agents --api-key /agents auth bypass. This report targets POST /api/mcp/connect in the PraisonAIUI host app.
• Not GHSA-9gm9-c8mq-vq7m / CVE-2026-34935 or GHSA-9qhq-v63v-fv3j / CVE-2026-41497. Those involve MCPHandler.parse mcp command() command parsing. This finding uses praisonaiui.server.api mcp connect -> praisonaiui.features.mcp.connect mcp server -> StdioMCPClient.
• Not GHSA-pj2r-f9mw-vrcq / CVE-2026-40159. That advisory concerns sensitive environment variables inherited by untrusted MCP subprocesses. This finding is unauthenticated network-triggered local process execution.
• Not GHSA-6rmh-7xcm-cpxj or GHSA-8444-4fhq-fxpq. Those concern unauthenticated legacy/generated agent servers. This is a distinct UI route and a distinct sink that starts arbitrary local processes.
• Not GHSA-9cr9-25q5-8prj, GHSA-9mqq-jqxf-grvw, or other MCP server file-read/path-traversal advisories. This path is the UI MCP client connector, not PraisonAI's MCP server tool dispatcher.

Recommended Fix

1. Remove arbitrary command/args from the remote HTTP API. MCP stdio servers should be configured only from trusted local configuration, not caller-supplied JSON.
2. Require authentication and authorization on /api/mcp/connect, /api/mcp/disconnect/*, and /api/mcp/servers regardless of AUTH ENFORCE.
3. Change UI command defaults from 0.0.0.0 to 127.0.0.1, or require an explicit --unsafe-expose style flag when binding externally without auth.
4. If remote MCP registration is a required feature, allow only URL-based transports with SSRF protections, or maintain an administrator-configured allowlist of commands.
5. Add regression tests that unauthenticated requests to /api/mcp/connect cannot start a subprocess, including when AUTH ENFORCE is unset.

Correção

OS Command Injection

Missing Authentication

Enumeração de Fraquezas

CWE-78

CWE-306

Identificadores relacionados

CVE-2026-57124

GHSA-P75F-6FP4-P57W

PYSEC-2026-3517

Produtos afetados

Praisonai

Referências · 7

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-p75f-6fp4-p57w · Nota
• https://github.com/MervinPraison/PraisonAI · Nota
• https://osv.dev/vulnerability/GHSA-p75f-6fp4-p57w · Aviso do Fabricante
• https://osv.dev/vulnerability/PYSEC-2026-3517 · Aviso do Fabricante
• https://nvd.nist.gov/vuln/detail/CVE-2026-57124 · Nota de Segurança
• https://pypi.org/project/praisonai · Nota
• https://github.com/advisories/GHSA-p75f-6fp4-p57w · Nota