Authenticated command execution via date parameter injection
Published Aug 8, 2026 · Updated Aug 8, 2026
Command injection in MCP Gateway allows remote authenticated users to execute host commands through the Claude usage range endpoint. getUsageByDateRange appends caller-controlled since and until values to an npx ccusage shell string and passes the result to execAsync without date validation or argument separation. Reachability requires the optional Claude Usage feature to be enabled; injected commands run with the gateway process account on the host.
Summary
What happened
Command injection in MCP Gateway allows remote authenticated users to execute host commands through the Claude usage range endpoint. getUsageByDateRange appends caller-controlled since and until values to an npx ccusage shell string and passes the result to execAsync without date validation or argument separation. Reachability requires the optional Claude Usage feature to be enabled; injected commands run with the gateway process account on the host.
The record
- CVE
- CVE-2026-19268
- Published
- Aug 8, 2026
- Updated
- Aug 8, 2026
- Vendor
- Abdullah Sarfaraz
- Product
- MCP Gateway
- Classifications
- CWE-77, CWE-74, T1059
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 8, 2026CVE publishedPublication date reported by the CVE source.
- Aug 8, 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=549f494a9e363f40530149de324b8097de424230
What conditions does exploitation require?
What is affected?
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
- Claude Usage range endpoint command-injection proof of conceptproof 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