Skip to main content

MCP Atlassian EUVDEUVD-2026-84605

| CVE-2026-77270 MEDIUM
Path Traversal (CWE-22)
2026-09-22 GitHub_M GHSA-f26r-j276-ggg4
6.5
CVSS 3.1 · Vendor: GitHub_M
View

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain

  1. Access
    Obtain MCP caller access with upload rights
  2. Delivery
    Invoke jira/confluence upload_attachment with malicious file_path
  3. Exploit
    Server opens arbitrary local file (open rb)
  4. Execution
    File uploaded to attacker-controlled issue/page
  5. Impact
    Download attachment to exfiltrate contents

Vulnerability Assessment

Weakness
CWE
OWASP Top 10:2025
A01:2025 - Broken Access Control
ASVS 5.0
V5 - File Handling Path canonicalization, traversal prevention
MITRE ATT&CK

2 techniques across 2 tactics: Discovery, Collection

The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up.

Exploitation Conditions

Requires an MCP caller that is authorized to invoke the Jira (jira_upload_attachment) or Confluence (confluence_upload_attachment) attachment-upload tools against the MCP Atlassian server prior to 0.22.0 (PR:L, network-reachable). No user interaction and no special non-default configuration is needed - the vulnerable code trusts any caller-supplied file_path and, before the fix, only converted relative paths to absolute (os.path.abspath) without confining them to a workspace. Impact is limited to files readable by the server process account, and exploitation is gated by having upload authorization; the danger is greatest in shared-credential or multi-tenant deployments where a low-privilege caller can thereby read host secrets (tokens, keys, config) beyond its intended Atlassian scope.

Impact

This is a genuine but moderate-priority issue, well-calibrated at CVSS 6.5. The vendor vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N is consistent with the description: an authenticated MCP caller (PR:L) with attachment-upload access can read arbitrary server-local files, yielding a confidentiality-only impact (C:H, I:N, A:N). No EPSS score, no CISA KEV listing, and no public exploit were provided, so this is no public exploit identified at time of analysis - not active exploitation. The realistic risk is bounded by the required upload authorization and by the still-emerging deployment footprint of this niche OSS project; it is not an internet-wide unauthenticated RCE. The one metric worth scrutiny is Scope: because the flaw lets a caller read files entirely outside the intended Atlassian data domain (any file the server process can read, e.g. /etc, credentials, keys), an S:C argument is defensible, which would raise the score; the sibling Confluence-only advisory CVE-2026-77258 was in fact scored S:C. I retain S:U to match the vendor but flag the ambiguity. Priority elevates in shared-credential/multi-tenant deployments where a low-privilege caller can exfiltrate host secrets.

Exploit ScenarioDerived

An MCP client authorized to use the Jira or Confluence attachment-upload tools supplies file_path=/etc/passwd (or a path to a service-account token, SSH key, or .env file) instead of a legitimate attachment. The server opens that file and uploads it to an attacker-controlled issue or page, after which the attacker downloads the attachment to read the contents. No public exploit code was identified, but the flaw is trivially reproducible given the described open(file_path, 'rb') sink and the low attack complexity (AC:L).

This Month Plan within 30 days. Why: MEDIUM severity (CVSS 4.0-6.9).
Patch available 0.5% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Sep 22, 2026

Path traversal in the MCP Atlassian MCP server (all versions prior to 0.22.0) allows an authenticated MCP caller that is authorized to invoke the Jira or Confluence attachment-upload tools to read arbitrary files as the server process. The upload tools accept a caller-supplied file_path and, before the fix, only normalised it with os.path.abspath without confining it to a workspace, so any path readable by the server account - tokens, keys, configuration - can be packaged and exfiltrated to an Atlassian issue or page; CVSS 6.5 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N) reflects high confidentiality loss but no integrity or availability impact, and no public exploit code has been identified at time of analysis. The issue matters most in shared-credential or multi-tenant deployments, where a low-privilege caller gains read access far beyond its intended Atlassian scope.

RemediationAI

Vendor-released patch: upgrade to MCP Atlassian 0.22.0 (https://github.com/sooperset/mcp-atlassian/releases/tag/v0.22.0), which introduces validate_safe_path() in the Confluence and Jira attachment upload handlers so caller-supplied file_path values are confined to the workspace; the equivalent upstream fix is PR #1448 / commit b041733473f95119dd539542a43c280737a8e460 and is described in advisory GHSA-f26r-j276-ggg4. If immediate upgrade is not possible, the most direct compensating control is to run the MCP server under a dedicated low-privilege account whose filesystem read access is restricted to an explicit allowlist directory - this does not stop traversal within that boundary but sharply limits what can be exfiltrated, at the cost of possibly breaking legitimate uploads of files stored elsewhere. Second, restrict which MCP callers may invoke confluence_upload_attachment and jira_upload_attachment (gate the tools behind per-user credentials rather than a shared token, or disable the upload tools entirely if unused), which removes the PR:L prerequisite that the exploit depends on; the trade-off is loss of upload functionality for authorised users. Third, keep the process working directory and any mounted secrets directory free of credentials the server does not need, and rotate Atlassian tokens and API keys stored on the host, since any file readable by the process prior to upgrading should be treated as potentially disclosed. Note that the upstream pull request also fixes related SSRF, CQL space-allowlist, and download-target issues, so partial backporting of only the path-confinement change is not recommended.

Affected VersionsENISA

mcp-atlassian < 0.22.0

Affected Packages

pypi mcp-atlassian fix: 0.22.0

Source: OSV (Open Source Vulnerabilities)

Affects your stack

Affects 1 package in pypi

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Technical ContextAI · show details

MCP Atlassian is a Python Model Context Protocol server that brokers Jira and Confluence operations for MCP clients; the affected code paths are the Confluence and Jira attachment upload tools (confluence_upload_attachment, jira_upload_attachment) which take a caller-controlled file_path argument and hand it to open(file_path, "rb") before streaming the bytes to an issue or page. The root cause is CWE-22 (Improper Limitation of a Pathname to a Restricted Directory), a canonical path-traversal / arbitrary-file-read pattern: the original implementation in src/mcp_atlassian/confluence/attachments.py converted relative paths to absolute with os.path.abspath, which resolves '..' segments and absolute paths but does not restrict them to any trusted root, so '../../etc/passwd' or '/home/user/.ssh/id_rsa' were both accepted. The fix replaces that with validate_safe_path(file_path), which confines upload sources to the workspace and rejects traversal or absolute paths that escape the current working directory. The same upstream pull request bundles adjacent hardening that is relevant context for defenders: an SSRF redirect hook and DNS-pinning adapter mounted on the Confluence session (closing a validate-then-reconnect TOCTOU), a change making the configured spaces_filter a hard allowlist that caller-supplied CQL can only narrow and never replace, and a guard refusing to download attachments into the working-directory root (where a written .py file could be imported and executed, GHSA-6vmq). CPE cpe:2.3:a:sooperset:mcp-atlassian:*:*:*:*:*:*:*:* tracks the wildcard-before-0.22.0 version range.

Know when Mcp Atlassian gets its next vulnerability

  • Watch products and get an email when something new is published
  • Check this CVE against your own stack and servers
  • Exploit and PoC references, threat intelligence from 22 sources

No credit card · 7-day full trial

Severity by source

Vendor (GitHub_M) PRIMARY 6.5 MEDIUM
AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
vuln.today AI 6.5 MEDIUM

Network-reachable MCP tool callable with low-privilege upload access (PR:L, AC:L); arbitrary server-file read gives C:H with no integrity or availability impact; S:U retained though S:C is arguable given cross-domain file exposure.

3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
4.0 AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (GitHub_M).

CVSS VectorVendor: GitHub_M

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None

Lifecycle Timeline

1
Patch available
Sep 22, 2026 - 19:02 EUVD

DescriptionCVE.org

MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, the Jira and Confluence attachment upload tools treat caller-controlled file_path values as trusted server-local paths. The server opens the selected file and uploads it to an Atlassian issue or page, allowing an MCP caller with upload access to disclose any file readable by the server process. The advisory traces the vulnerable input and processing flow through confluence_upload_attachment, jira_upload_attachment, file_path, and open(file_path, "rb"), which identify the affected entry points, controls, and code paths. This issue is fixed in version 0.22.0.

Threat Intelligence Overview

EPSS Score
0.5%
Top 59% exploitable
Prevalence
Low
niche open-source Atlassian MCP server, emerging AI-tooling adoption, limited production footprint
Threat Intel
1
1 source
Exploit
POC
Public exploit code exists
Data Quality
6 sources
Confidence: High

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue
Severity MEDIUM
CISA KEV No
Public POC Yes
EPSS 0.5%
Patch available Yes
Active threat No
Deciding rule
MEDIUM severity (CVSS 4.0-6.9)
What every action level means
Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.
Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.
This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.
This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.
Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision· derived
Scheduled
Exploitation
Poc
System Exposure· derived
Open
Automatable
No
Human Impact· derived
Medium
Technical Impact
Partial

Priority Score

52
Low Medium High Critical
KEV: 0
EPSS: 0
CVSS: +32
PoC: +20
Weaponized: 0
Threat intel: 0
Gov advisory: 0

Attack Technique

Path traversal exploits occur when applications use user-controlled input to construct file system paths without proper validation.

CVE-2026-77274 HIGH POC
8.8 Sep 22

Server-side request forgery in MCP Atlassian (the Model Context Protocol server for Confluence and Jira) prior to 0.22.0

CVE-2026-77243 HIGH POC
8.8 Sep 22

MCP Atlassian (sooperset/mcp-atlassian) before 0.22.0 applies its ENABLED_TOOLS and TOOLSETS least-privilege filters onl

CVE-2026-77262 HIGH POC
8.6 Sep 22

Path traversal in MCP Atlassian releases prior to 0.22.0 lets a caller of the confluence_upload_attachment MCP tool read

CVE-2026-77248 HIGH POC
8.6 Sep 22

Unauthenticated arbitrary file read in MCP Atlassian (sooperset/mcp-atlassian) before 0.22.0 lets a remote network calle

CVE-2026-77255 HIGH POC
8.6 Sep 22

Arbitrary local file read leading to data exfiltration affects sooperset's MCP Atlassian server (mcp-atlassian) prior to

CVE-2026-77246 HIGH POC
8.6 Sep 22

Unauthenticated server-local file exfiltration in MCP Atlassian (sooperset/mcp-atlassian) before 0.22.0 allows a remote

CVE-2026-77261 HIGH POC
8.5 Sep 22

Server-side request forgery in MCP Atlassian prior to 0.22.0 lets an attacker who controls or has already compromised th

CVE-2026-77271 HIGH POC
8.3 Sep 22

MCP Atlassian (sooperset/mcp-atlassian) before 0.22.0 lets a low-privileged authenticated MCP caller write attacker-chos

CVE-2026-77267 HIGH POC
8.3 Sep 22

Server-side request forgery in MCP Atlassian (sooperset/mcp-atlassian) before 0.22.0 allows a low-privileged authenticat

CVE-2026-77257 HIGH POC
8.3 Sep 22

Arbitrary local file read in MCP Atlassian (mcp-atlassian) prior to 0.22.0 allows an authenticated MCP caller who can re

CVE-2026-77260 HIGH POC
8.3 Sep 22

Arbitrary server-local file read and exfiltration in MCP Atlassian (sooperset/mcp-atlassian) prior to 0.22.0 lets an aut

CVE-2026-77247 HIGH POC
8.3 Sep 22

Path traversal in the MCP Atlassian server (mcp-atlassian) prior to 0.22.0 allows an authenticated MCP client to read fi

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy