# MCP Atlassian: Path traversal in upload_attachment allows arbitrary file read and exfiltration via MCP tool call

Advisory record · `GHSA-mfv2-4wvm-9pgp`

- **Identifiers:** `GHSA-mfv2-4wvm-9pgp` · `CVE-2026-77266` · `PYSEC-2026-4097`
- **State:** Confirmed
- **Severity:** CVSS 6.5 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-22](https://cwe.mitre.org/data/definitions/22.html)
- **Tags:** [Path traversal](https://agentprime.io/advisories/tag/path-traversal.md)
- **Published:** 22 Sept 2026
- **Updated:** 1 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 22 Sept 2026, 20:35 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `mcp-atlassian` (PyPI): affected `<0.22.0`; fixed in `0.22.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> The mcp-atlassian package, versions before 0.22.0, has a path traversal flaw in its Jira and Confluence upload_attachment tools: the file_path parameter is opened without the path validation used on download. An authenticated MCP client can therefore make the server read arbitrary files it can access, such as system files or stored tokens, and upload them to the Atlassian instance as attachments. Upgrade to mcp-atlassian 0.22.0 or later, which contains the fix.

Written 1 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 6.5 Medium, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0050, the 43rd percentile, on 11 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:09 UTC: First seen by agentprime
- 31 Oct 2026, 14:09 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-mfv2-4wvm-9pgp)

## Sources

- [GitHub Advisory Database: GHSA-mfv2-4wvm-9pgp](https://github.com/advisories/GHSA-mfv2-4wvm-9pgp)
- [OSV: GHSA-mfv2-4wvm-9pgp](https://osv.dev/vulnerability/GHSA-mfv2-4wvm-9pgp)
- <https://github.com/sooperset/mcp-atlassian/security/advisories/GHSA-mfv2-4wvm-9pgp>
- <https://github.com/sooperset/mcp-atlassian/pull/1448>
- <https://github.com/sooperset/mcp-atlassian/commit/b041733473f95119dd539542a43c280737a8e460>
- <https://github.com/sooperset/mcp-atlassian>
- <https://github.com/sooperset/mcp-atlassian/releases/tag/v0.22.0>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-mfv2-4wvm-9pgp>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-mfv2-4wvm-9pgp/>. Everything for agents: <https://agentprime.io/llms.txt>.
