Remote code execution via unsanitized WebSocket path
Published Apr 26, 2026 · Updated Apr 26, 2026
OS command injection in AgentDeskAI BrowserTools MCP 1.2.0 and earlier allows remote attackers to execute commands through its WebSocket API. The browser connector embeds an unescaped WebSocket path in AppleScript and passes the resulting script to a shell. The default unauthenticated listener is reachable from visited web pages or the local network; code execution requires macOS with auto-paste enabled.
Summary
What happened
OS command injection in AgentDeskAI BrowserTools MCP 1.2.0 and earlier allows remote attackers to execute commands through its WebSocket API. The browser connector embeds an unescaped WebSocket path in AppleScript and passes the resulting script to a shell. The default unauthenticated listener is reachable from visited web pages or the local network; code execution requires macOS with auto-paste enabled.
The record
- CVE
- CVE-2026-7064
- Published
- Apr 26, 2026
- Updated
- Apr 26, 2026
- Vendor
- AgentDeskAI
- Product
- BrowserTools MCP
- Classifications
- CWE-78, CWE-77, T1059.002
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 26, 2026CVE publishedPublication date reported by the CVE source.
- Apr 26, 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=1.0
- Affected versionversion=1.1
- Affected versionversion=1.2.0
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
- browser-tools-mcp OS Command Injection Vulnerabilityproof of concept · unverified
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