AgentDeskAI browser-tools-mcp up to 1.2.0 browser-connector.ts os command injection

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
6.9$0-$5k0.18

Summaryinfo

A vulnerability was found in AgentDeskAI browser-tools-mcp up to 1.2.0. It has been rated as critical. Impacted is an unknown function of the file browser-tools-server/browser-connector.ts. The manipulation leads to os command injection. This vulnerability is traded as CVE-2026-7064. It is possible to initiate the attack remotely. Furthermore, there is an exploit available. Upgrading the affected component is advised.

Detailsinfo

A vulnerability was found in AgentDeskAI browser-tools-mcp up to 1.2.0. It has been rated as critical. This issue affects an unknown function of the file browser-tools-server/browser-connector.ts. The manipulation with an unknown input leads to a os command injection vulnerability. Using CWE to declare the problem leads to CWE-78. The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component. Impacted is confidentiality, integrity, and availability.

The weakness was shared by researchersongwu as 224 / 232 / GHSA-xvrv-w8pg-f25f. It is possible to read the advisory at github.com. The identification of this vulnerability is CVE-2026-7064. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. Technical details as well as a public exploit are known. The attack technique deployed by this issue is T1202 according to MITRE ATT&CK.

The exploit is available at github.com. It is declared as proof-of-concept.

Upgrading to version 2.0.0 eliminates this vulnerability. The upgrade is hosted for download at github.com.

The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2026-25734). github.com is providing further details. Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Type

Vendor

Name

Version

Website

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA CVSS-B Score: 🔒
CNA CVSS-BT Score: 🔒
CNA Vector: 🔒

CVSSv3info

VulDB Meta Base Score: 7.3
VulDB Meta Temp Score: 6.9

VulDB Base Score: 7.3
VulDB Temp Score: 6.6
VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA Base Score: 7.3
CNA Vector: 🔒

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍

Exploitinginfo

Class: Os command injection
CWE: CWE-78 / CWE-77 / CWE-74
CAPEC: 🔒
ATT&CK: 🔒

Physical: No
Local: No
Remote: Yes

Availability: 🔒
Access: Public
Status: Proof-of-Concept
Download: 🔒

EPSS Score: 🔒
EPSS Percentile: 🔒

Price Prediction: 🔍
Current Price Estimation: 🔒

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: Upgrade
Status: 🔍

0-Day Time: 🔒

Upgrade: browser-tools-mcp 2.0.0

Timelineinfo

04/26/2026 Advisory disclosed
04/26/2026 +0 days VulDB entry created
10/04/2026 +161 days VulDB entry last update

Sourcesinfo

Product: github.com

Advisory: 224 / 232 / GHSA-xvrv-w8pg-f25f
Researcher: researchersongwu
Status: Confirmed
Confirmation: 🔒

CVE: CVE-2026-7064 (🔒)
GCVE (CVE): GCVE-0-2026-7064
GCVE (VulDB): GCVE-100-359639
EUVD: 🔒
scip Labs: https://www.scip.ch/en/?labs.20161013
Misc.: 🔒

Entryinfo

Created: 04/26/2026 09:15
Updated: 10/04/2026 05:33
Changes: 04/26/2026 09:15 (57), 04/27/2026 04:17 (1), 10/02/2026 05:34 (2), 10/02/2026 05:35 (1), 10/02/2026 15:31 (14), 10/04/2026 05:33 (31)
Complete: 🔍
Submitter: MidA
Cache ID: 216::103

Submitinfo

Accepted

  • Submit #798616: AgentDeskAI browser-tools-mcp 1.2.0 OS Command Injection (by MidA)

Duplicate

Be aware that VulDB is the high quality source for vulnerability data.

Discussion

 researchersongwu (+0)
3 days ago
I believe the current handling and attribution of this vulnerability are incorrect and should be formally reviewed and corrected.

I reported this vulnerability to the official project on GitHub on [March 14](https://github.com/AgentDeskAI/browser-tools-mcp/issues/224#issue-4074839737). The other applicant submitted their report later, on [April 7](https://github.com/AgentDeskAI/browser-tools-mcp/issues/232#issue-4216522955).

More importantly, this is not merely a matter of comparing submission dates. The project maintainer explicitly confirmed that the later report was a duplicate of my earlier report. In response to Issue #232, the maintainer stated:

> “Fixed in 2.0.0, and thank you for the writeup. Duplicate of #224, tracking there. On your CVE request: a GitHub Security Advisory is now published at GHSA-xvrv-w8pg-f25f and a CVE has been requested through it — I will post the identifier here once assigned. Details of the fix are in #224 and in SECURITY.md.”

This statement is unambiguous: Issue #232 was considered a duplicate of my Issue #224, and the vulnerability was being tracked through my earlier report.

The corresponding GitHub Security Advisory is also available here:

[GHSA-xvrv-w8pg-f25f](https://github.com/AgentDeskAI/browser-tools-mcp/security/advisories/GHSA-xvrv-w8pg-f25f)

In addition, the project maintainer formally credited me on GitHub for the original vulnerability disclosure.

Given this evidence, I do not believe it is reasonable to attribute the vulnerability to the later applicant, or to treat the two reports as if they had equal priority. The project maintainer has already established the reporting history and explicitly identified the later submission as a duplicate.

I therefore request that you review the attribution for this vulnerability and correct the reporter credit accordingly.

Please verify the following evidence directly:

1. My original report, Issue #224, was submitted on March 14.
2. Issue #232 was submitted later, on April 7.
3. The project maintainer explicitly stated that Issue #232 is a “Duplicate of #224.”
4. The maintainer stated that the fix details are tracked in Issue #224 and SECURITY.md.
5. The related GitHub Security Advisory is GHSA-xvrv-w8pg-f25f.
6. I was formally credited by the project maintainer for the original disclosure.

Based on the project's own public record, the reporting priority is clear. I therefore ask that the current attribution be corrected to reflect the original report and the maintainer's documented determination.

Thank you for reviewing and correcting this matter.
 VulDB Community Team3 days ago
Thank you for your feedback. We have updated the entry accordingly.

◂ PreviousOverviewNext ▸

Do you need the next level of professionalism?

Upgrade your account now!