CVE-2026-73498
If an AI agent can be induced to call the tool through untrusted content, the same flaw can disclose server environment variables such as CONFLUENCE_API_TOKEN and other credentials.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.33%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, confluence_upload_attachment passes its client-supplied file_path directly to open(file_path, "rb") in src/mcp_atlassian/confluence/attachments.py through _upload_attachment_direct() without calling validate_safe_path. An authenticated MCP client can read any file accessible to the server process and exfiltrate it to Confluence as an attachment. If an AI agent can be induced to call the tool through untrusted content, the same flaw can disclose server environment variables such as CONFLUENCE_API_TOKEN and other credentials. This issue is fixed in version 0.22.0.
- CVSS 3.1
- 7.7 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- EPSS
- 0.33% probability · 26th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-22
- Source
- security-advisories@github.com
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-g5r6-gv6m-f5jv
- https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-g5r6-gv6m-f5jv
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.