CVE-2026-27825
9.0 · CRITICALOverview
CVE-2026-27825 is a critical-severity vulnerability affecting mcp-atlassian mcp_atlassian. It was published on March 10, 2026 and has a CVSS 3.1 base score of 9.0 (CRITICAL).
This vulnerability has a CVSS 3.1 base score of 9.0, rated CRITICAL. It requires local or adjacent network access to exploit. Some level of privileges is required for exploitation.
Technical Description
MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to version 0.17.0, the `confluence_download_attachment` MCP tool accepts a `download_path` parameter that is written to without any directory boundary enforcement. An attacker who can call this tool and supply or access a Confluence attachment with malicious content can write arbitrary content to any path the server process has write access to. Because the attacker controls both the write destination and the written content (via an uploaded Confluence attachment), this constitutes for arbitrary code execution (for example, writing a valid cron entry to `/etc/cron.d/` achieves code execution within one scheduler cycle with no server restart required). Version 0.17.0 fixes the issue.
Remediation
Check the references section for vendor advisories and patches from mcp-atlassian. Update mcp_atlassian to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
Affected Products
| Vendor | Product | Versions | Status |
|---|---|---|---|
| mcp-atlassian | mcp_atlassian | >= 0, < 0.17.0 | Affected |
Frequently Asked Questions
What is CVE-2026-27825?
CVE-2026-27825 is a critical-severity vulnerability affecting mcp-atlassian mcp_atlassian. It was published on March 10, 2026 and has a CVSS 3.1 base score of 9.0 (CRITICAL).
How severe is CVE-2026-27825?
This vulnerability has a CVSS 3.1 base score of 9.0, rated CRITICAL. It requires local or adjacent network access to exploit. Some level of privileges is required for exploitation.
How do I fix or remediate CVE-2026-27825?
Check the references section for vendor advisories and patches from mcp-atlassian. Update mcp_atlassian to the latest patched version. If immediate patching is not possible, review the CVSS vector to understand the attack surface and apply compensating controls such as network segmentation or access restrictions.
How can CyberStrike help with CVE-2026-27825?
CyberStrike's AI-powered security agents can automatically detect CVE-2026-27825 across your infrastructure using autonomous pentesting, DAST scanning, and HackBrowser. The platform continuously monitors for known vulnerabilities and provides actionable remediation guidance prioritized by real-world exploitability.
How CyberStrike Helps
AI agents map your attack surface to find vulnerabilities like this one.
Automated penetration testing that runs continuously, not just quarterly.
AI-driven PR review catches vulnerable dependencies before they ship.
Browser-based exploitation validates findings with real proof-of-concept.
Related CRITICAL CVEs from 2026
View all →A command injection vulnerability in the execute_command function of terminal-controller-mcp 0.1.7 a
n8n is an open source workflow automation platform. Versions starting with 1.65.0 and below 1.121.0
Fastjson before 1.2.48 mishandles autoType because, when an @type key is in a JSON document, and the
This vulnerability allows authenticated attackers to execute commands via the hostname of the device
Remote Code Execution vulnerability that allows unauthenticated attackers to inject arbitrary comman
XWiki Full Calendar Macro displays objects from the wiki on the calendar. Prior to version 2.4.5, us
Successful exploitation of the SQL injection vulnerability could allow an unauthenticated remote att
A static password reset token in the password reset function of DDSN Interactive Acora CMS v10.7.1 a
Affected devices do not properly enforce user authentication on specific API endpoints. This could f
Sandbox escape in the Messaging System component. This vulnerability was fixed in Firefox 147 and Th
OpenC3 COSMOS provides the functionality needed to send commands to and receive data from one or mor
Enclave is a secure JavaScript sandbox designed for safe AI agent code execution. Prior to 2.7.0, th