Disclosed weakness · no CVE recorded
Atlassian MCP filters could disclose content from excluded projects or spaces
mcp-atlassian maintainers · mcp-atlassian · Jira and Confluence MCP server
First documented disclosure · Review checkpoint
Summary
Jira changelogs and Confluence content could include information from outside an operator’s project or space filters.
Severity and exploitation evidence
Medium · numeric CVSS score not recorded. Severity source.
Exploitation not established: The maintainer reports an internal audit finding. The advisory identifies no malicious use.
Technical severity is not a measure of observed attacks or of risk to your deployment. Attempts, demonstrations, and successful compromise retain the qualifications in the source.
How the weakness works
Several paths skipped checks on empty scoped arguments, returned unfiltered related content, or failed to account for a moved issue.
Conditions required
A filtered deployment uses a credential with access to additional Atlassian data.
Potential impact
Callers could read out-of-scope metadata or content available to the credential.
Affected versions and configurations
Before 0.24.5.
Fix and mitigation status
0.24.5.
Practical next steps
Upgrade to 0.24.6 or later. Use a credential whose Atlassian permissions match the intended scope.
Operating lesson
Check both the input scope and the related objects returned by a tool.
Evidence and limits
The maintainer traced this issue to an internal audit and published the patch and advisory November 16. The advisory provides a severity label without a numeric score.
Sources
- mcp-atlassian public correction
Primary source ·
- mcp-atlassian 0.24.5 release notes
Primary source ·
- mcp-atlassian advisory GHSA-vhwv-5pg8-hh56
Primary source ·