Skip to main content
Press slash or control plus K to focus the search. Use the arrow keys to navigate results and press enter to open a threat.
Reconnecting to live updates…

LangBot: Authenticated RCE Via MCP Configuration (CVE-2026-54449)

0
High
Published: 07/15/2026 (07/15/2026, 17:39:34 UTC)
Source: GCVE Database
Product: langbot

Description

LangBot versions up to and including 4.10.5 contain an authenticated remote code execution vulnerability. An authenticated user can modify the MCP Server Configuration to add an "STDIO" MCP that executes arbitrary commands on the server. This occurs due to unsafe use of StdioServerParameters which runs subprocess commands based on user input. Exploitation can lead to full system compromise including data exfiltration, reverse shells, or destructive actions.

CVSS v3.1

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected software

PyPIghsa
langbot
Affected versions
<=4.10.5

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 07/18/2026, 12:41:25 UTC

Technical Analysis

The vulnerability in LangBot (CVE-2026-54449) allows any authenticated user to achieve remote code execution by modifying the MCP Server Configuration to add an "STDIO" MCP with arbitrary commands. This is caused by the use of StdioServerParameters that executes subprocess commands derived from user input without sufficient validation or sanitization. The flaw affects all LangBot versions up to and including 4.10.5. Exploitation requires authentication but can result in high impact including full system compromise. The CVSS 3.1 vector is AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H indicating network attack vector, low attack complexity, privileges required, no user interaction, unchanged scope, and high confidentiality, integrity, and availability impact.

Potential Impact

Successful exploitation allows an authenticated user to execute arbitrary commands on the server hosting LangBot, potentially leading to full system compromise. This includes the ability to exfiltrate data, establish reverse shells, or perform destructive operations, severely impacting confidentiality, integrity, and availability of the system.

Mitigation Recommendations

No official patch or fix is currently available for this vulnerability. Users should restrict authentication access to trusted personnel only and monitor for suspicious configuration changes. Patch status is not yet confirmed — check the vendor advisory for current remediation guidance.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Gcve Source
db.gcve.eu
Osv Id
GHSA-3pvh-63gf-j9mw
Osv Schema Version
1.4.0
Aliases
["CVE-2026-54449"]
Ecosystems
["PyPI"]
Database Specific Severity
HIGH
Cvss Version
3.1

Threat ID: 6a58b50e68715ace43db326a

Added to database: 07/16/2026, 10:40:14 UTC

Last enriched: 07/18/2026, 12:41:25 UTC

Last updated: 07/19/2026, 07:56:49 UTC

Views: 17

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses