CVE-2026-73498 json
MCP Atlassian is a Model Context Protocol (MCP): Arbitrary file read via missing path validation in confluence_upload_attachment
published 2026-07-10 4 mo ago modified 2026-10-24 16 d ago also EUVD-2026-57639 , GHSA-g5r6-gv6m-f5jv , PYSEC-2026-3683
- cvss
- 7.7
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.5%
- EPSS 0.5% chance of exploitation in 30 days, percentile 41%
- public exploits
- 0
- none known
Summary
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.
Patch / fix
- pypi mcp-atlassian 0.22.0
- mcp-atlassian mcp_atlassian 0.22.0
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- no
- Technical impact
- partial
- Assessed
- 2 mo ago
Exploit prediction
0.48% chance of exploitation in the next 30 days, higher than 41% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-g5r6-gv6m-f5jv referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 7.7 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N |
| GitHub | 3.1 | 7.7 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N |
| OSV | 3.1 | 7.7 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | mcp-atlassian | <0.22.0 |
0.22.0 |
Affected products
- sooperset mcp-atlassian
Classification
- Weakness
-
- CWE-22 Improper Limitation of a Pathname to a Restricted Directory
References
- github.com /sooperset/mcp-atlassian/pull/1448
-
github.com
/sooperset/mcp-atlassian/commit/b041733473f95119dd539542a43c280737a8e460
web
-
github.com
/sooperset/mcp-atlassian/security/advisories/GHSA-g5r6-gv6m-f5jv
exploit, web
-
github.com
/sooperset/mcp-atlassian/releases/tag/v0.22.0
web
-
github.com
/sooperset/mcp-atlassian
package
-
pypi.org
/project/mcp-atlassian
package
-
github.com
/advisories/GHSA-g5r6-gv6m-f5jv
advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-73498
advisory
Sources
- CVE List CVE-2026-73498
- GitHub Advisory GHSA-g5r6-gv6m-f5jv
- NVD CVE-2026-73498
- OSV PYSEC-2026-3683
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.