CVE-2026-77255
8.6 HIGHpublic exploit availablePublished 2026-09-22 · Updated 2026-09-26
AI risk analysis
- Summary
- This flaw allows an attacker to read arbitrary local files and attach them to a Jira issue by exploiting the MCP Atlassian server prior to version 0.22.0, leading to potential data exfiltration.
- Exploitability
- Exploitation is moderately hard as it requires crafting a specific input to the Jira update_issue attachments argument, and the attacker must have the ability to interact with the MCP server.
- Blast radius
- If exploited, the impact is high as it could lead to unauthorized access to sensitive local files and their attachment to Jira issues, compromising data integrity and confidentiality.
- Detection
- No reliable host or network indicator is derivable from the published description.
- Prioritized remediation
- Upgrade to MCP Atlassian version 0.22.0 or later.
Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.
NVD description
MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, the Jira update_issue attachments argument is converted into local paths and routed to the attachment upload implementation without workspace validation. A caller can make the MCP server read arbitrary local files and attach them to a Jira issue, using the server as a confused deputy to exfiltrate the contents. The advisory traces the vulnerable input and processing flow through jira update_issue, attachments, upload_attachment, and file_path, which identify the affected entry points, controls, and code paths. This issue is fixed in version 0.22.0.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N
Weaknesses
CWE-22, CWE-441
Public exploit & PoC references
- https://github.com/sooperset/mcp-atlassian/commit/b041733473f95119dd539542a43c280737a8e460
- https://github.com/sooperset/mcp-atlassian/pull/1448
- https://github.com/sooperset/mcp-atlassian/releases/tag/v0.22.0
- https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-2xj6-xx86-cwwc
- https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-2xj6-xx86-cwwc
All references
- https://github.com/sooperset/mcp-atlassian/commit/b041733473f95119dd539542a43c280737a8e460
- https://github.com/sooperset/mcp-atlassian/pull/1448
- https://github.com/sooperset/mcp-atlassian/releases/tag/v0.22.0
- https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-2xj6-xx86-cwwc
- https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-2xj6-xx86-cwwc
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2025-1281
- HIGHCVE-2026-100520PoC
- HIGHCVE-2026-100682PoC
- HIGHCVE-2026-12609PoC
- HIGHCVE-2026-15979
- CRITICALCVE-2026-16940
- HIGHCVE-2026-46581PoC
- HIGHCVE-2026-60009PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.