Authenticated command execution via STDIO MCP configuration
Published Aug 20, 2026 · Updated Aug 20, 2026
Command injection in LangBot 4.10.7 and earlier allows remote authenticated users to execute arbitrary commands via STDIO MCP settings. In src/langbot/pkg/provider/tools/loaders/mcp.py, the Extensions MCP flow passes user-controlled command and arguments into StdioServerParameters, which starts a server-side subprocess from that input. Any user who can sign up or obtain an account can reach this setting and run code with the LangBot service's privileges, enabling data disclosure, data modification, or service disruption.
Summary
What happened
Command injection in LangBot 4.10.7 and earlier allows remote authenticated users to execute arbitrary commands via STDIO MCP settings. In src/langbot/pkg/provider/tools/loaders/mcp.py, the Extensions MCP flow passes user-controlled command and arguments into StdioServerParameters, which starts a server-side subprocess from that input. Any user who can sign up or obtain an account can reach this setting and run code with the LangBot service's privileges, enabling data disclosure, data modification, or service disruption.
The record
- CVE
- CVE-2026-54449
- Published
- Aug 20, 2026
- Updated
- Aug 20, 2026
- Vendor
- LangBot
- Product
- LangBot
- Classifications
- CWE-77, T1059
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 20, 2026CVE publishedPublication date reported by the CVE source.
- Aug 20, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=<= 4.10.7
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-3pvh-63gf-j9mw video PoC and reproduction stepsproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo