GHSA-3pvh-63gf-j9mw: LangBot: Authenticated RCE Via MCP Configuration
highvulnerabilityLLM-Specific
security
Summary
Authenticated users of LangBot can run any command they want on the server by adding a malicious STDIO MCP (a plugin system that executes external programs) through the Extensions settings. An attacker who logs in (either through their own account or stolen credentials) can configure the MCP to run arbitrary commands, giving them complete control over the machine.
Vulnerability Details
EPSS (30-day exploit probability)
EPSS: 0.0%
Disclosure Date
July 15, 2026
Classification
Attack Type
Supply Chain
Attack SophisticationModerate
Impact (CIA+S)
confidentialityintegrity
Taxonomy References
MITRE ATLAS (AI/ML Threat Technique)
Affected Vendors
Anthropic
Affected Packages
langbot@<= 4.10.5
Related Issues
Monthly digest — independent AI security research
Original source: https://github.com/advisories/GHSA-3pvh-63gf-j9mw
First tracked: July 15, 2026 at 02:01 PM
Classified by LLM (prompt v3) · confidence: 92%