Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-81735 – Unauthenticated Remote Command Execution – ByteDance UI-TARS-desktop (@agent-infra

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-81735 is a critical missing-authentication vulnerability (CWE-306) affecting the @agent-infra Model Context Protocol (MCP) server components bundled with ByteDance’s UI-TARS-desktop project. The mcp-http-server package’s startServer.ts defaults to listening on all network interfaces (::) without requiring authentication, meaning any client that can reach the exposed port can invoke the server’s command-execution and filesystem tools. The flaw carries the maximum CVSS score of 10.0 and permits full unauthenticated remote command execution.

Technical details

  • Root cause: startServer.ts in the mcp-http-server package binds the HTTP listener to :: (all interfaces) by default when no host is explicitly configured, and its authentication middleware is optional rather than enforced.
  • Trigger conditions: The @agent-infra/mcp-server-commands and @agent-infra/mcp-server-filesystem entry points start the HTTP server without ever supplying the authentication middleware, so no credential or token check is applied to incoming requests.
  • Attack vector: Network — any unauthenticated client that can route to the exposed port can call the server’s tools directly, including a run_command tool that executes arbitrary operating system commands, and filesystem tools that expose file read/write operations.
  • Impact: Complete compromise of confidentiality, integrity, and availability on the host running the MCP server, since an attacker can execute arbitrary commands and manipulate the filesystem without any authentication or user interaction.

Affected software

  • Vendor/Product: ByteDance – UI-TARS-desktop, @agent-infra MCP server packages (mcp-http-server, mcp-server-commands, mcp-server-filesystem)
  • Affected range: All versions/commits prior to the fixing commit c2ad42e3eb9b27830db41a3e6f51ca7179d9b168 (fixed via GitHub pull request #1918)
  • Fixed in: Commit c2ad42e3eb9b27830db41a3e6f51ca7179d9b168 and later

Severity

  • CVSS v3.1 Base Score: 10.0 (CRITICAL)
  • CVSS v3.1 Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
  • (A companion CVSS v4.0 score of 10.0 was also assigned: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H)

Mitigation and recommended actions

  • Immediate: Update UI-TARS-desktop and the affected @agent-infra MCP server packages to the version containing fix commit c2ad42e3eb9b27830db41a3e6f51ca7179d9b168 (merged via PR #1918) or later, which enforces authentication middleware on the MCP HTTP server.
  • If patching is not immediately possible:
    • Do not expose the MCP HTTP server (mcp-http-server / command / filesystem MCP servers) to untrusted networks; bind it explicitly to localhost/127.0.0.1 rather than the default all-interfaces listener.
    • Restrict access to the listening port via host-based firewall rules or network segmentation so only trusted local processes can reach it.
    • Audit hosts running UI-TARS-desktop or its @agent-infra MCP components for external exposure of the affected ports and for signs of unauthorized command execution or file access.
    • Where feasible, place the service behind a reverse proxy or VPN that enforces authentication until the patched version is deployed.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge