Disclosed weakness · no CVE recorded
Jira and Confluence tools could act outside their configured allowlists
mcp-atlassian maintainers · mcp-atlassian · Jira and Confluence MCP server
First documented disclosure · Review checkpoint
Summary
A tool could resolve an object outside the project or space the operator authorized.
Severity and exploitation evidence
High · 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
Certain tool arguments changed which Atlassian resource a request addressed after the server checked the allowlist.
Conditions required
A project or space filter is in use and a caller or model can supply a tool argument.
Potential impact
Out-of-scope objects could be read or, when writes are enabled, changed within the Atlassian credential’s permissions.
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. Scope the Atlassian credential to permitted projects or spaces. Read-only mode also limits writes.
Operating lesson
Authorize the resolved object that the upstream service will actually receive.
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-f5qp-f5cw-2r8f
Primary source ·