Skip to main content

MCP Atlassian EUVDEUVD-2026-84748

| CVE-2026-77269 MEDIUM
Path Traversal (CWE-22)
2026-09-22 GitHub_M GHSA-h7wj-5v37-59r2
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
    Gain permitted MCP caller access
  2. Delivery
    Call upload_attachment with traversal/absolute file_path
  3. Exploit
    Server reads arbitrary local file
  4. Execution
    File uploaded as Confluence/Jira attachment
  5. Impact
    Retrieve attachment to exfiltrate secrets

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 the attacker to be a permitted MCP caller able to invoke the attachment-upload tool (upload_attachment) against an MCP Atlassian server older than 0.22.0 configured with valid Confluence/Jira credentials - most impactful in shared-credential or multi-user/HTTP-transport deployments where a client can exercise the server's file system through the operator's credentials. The specific trigger is a caller-supplied absolute or path-traversal file_path to the upload flow, which the vulnerable code only abspath'd rather than validating against the workspace. Limiting factors: exploitation is bounded to files readable by the server process, requires the low-privilege ability to call the tool (PR:L, not fully unauthenticated), and yields confidentiality impact only (no write or availability effect); it is fully mitigated by upgrading to 0.22.0.

Impact

This is a genuine but bounded issue best rated MEDIUM. The CVSS 3.1 vector (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N = 6.5) is internally consistent with the description: a network-reachable MCP server, low attack complexity, and required low privilege (PR:L) because the attacker must be a permitted MCP client able to invoke the upload_attachment tool against configured Atlassian credentials. Impact is confidentiality-only (C:H, I:N, A:N) - the flaw reads and exfiltrates arbitrary host-readable files but does not modify or crash the system. No EPSS score, no CISA KEV listing, and no public exploit code are provided, so this is no public exploit identified at time of analysis; there is no signal of active or widespread exploitation. Notably, this is explicitly framed as an incomplete-fix/bypass of CVE-2026-27825: that prior remediation constrained download destinations but left upload SOURCE paths (file_path) unvalidated, a classic asymmetric-fix gap confirmed by the vendor advisory and PR diff. Net: real and worth patching for anyone running MCP Atlassian, but not an emergency mass-exploitation candidate given PR:L gating, confidentiality-only impact, and the niche deployment footprint.

Exploit ScenarioDerived

An attacker who can reach the MCP Atlassian server as a permitted caller (e.g., through a shared-credential or multi-user MCP deployment) invokes the attachment-upload tool with an absolute or traversal file_path such as '/etc/passwd', '../../.env', or a mounted secrets file. The server reads that local file and uploads it as an attachment to a Confluence page or Jira issue, from which the attacker reads it back, exfiltrating server-side secrets and configuration. No public exploit code is provided, but the technique is trivial given low attack complexity.

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

Authenticated path traversal in MCP Atlassian (mcp-atlassian) prior to 0.22.0 lets a permitted MCP caller supply an absolute or traversal-laden file_path to the Confluence attachment-upload flow and cause the server to read and upload an arbitrary local file using the operator's credentials, exposing file contents to the linked Confluence instance. The flaw is a direct gap left by the CVE-2026-27825 fix, which hardened download destinations but never constrained upload source paths; only confidentiality is affected (no write or availability impact), and exploitation is bounded to files readable by the server process. No public exploit identified at time of analysis, and the issue is fully resolved by upgrading to 0.22.0.

RemediationAI

Vendor-released patch: 0.22.0 - upgrade mcp-atlassian to 0.22.0 or later (https://github.com/sooperset/mcp-atlassian/releases/tag/v0.22.0), which replaces the abspath()-only handling in upload_attachment with validate_safe_path() and confines upload sources to the workspace; the specific change is visible in commit b041733473f95119dd539542a43c280737a8e460 and PR 1448, and full context is in advisory GHSA-h7wj-5v37-59r2. Note that PR 1448 also ships related hardening (DNS pinning/SSRF redirect hooks, an AND-only spaces filter, and a refusal to download into the working-directory root), so upgrading picks up additional protections with no expected functional regression for legitimate callers - the main side effect is that attachment uploads referencing files outside the workspace, which some operators may have relied on, will now be rejected. If immediate upgrade is not possible, compensating controls are constrained but effective: run the MCP server as a dedicated low-privilege OS account or inside a container with only the specific attachment directories bind-mounted, so traversal can reach nothing sensitive (trade-off: legitimate access to other file locations must be re-provisioned as explicit mounts); restrict which clients can reach the MCP endpoint and prefer per-user rather than shared credentials so PR:L access is not amplified to the operator's full Confluence/Jira rights (trade-off: added credential-management overhead and possible loss of convenience features); and, in shared-credential or HTTP-transport deployments, disable or gate the attachment-upload tool entirely until patched (trade-off: loss of attachment-upload functionality). Because only confidentiality is affected and exploitation requires an already-permitted tool caller, no network-layer mitigation beyond access restriction is required.

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 Model Context Protocol server that exposes Confluence and Jira operations as tools to MCP clients, so a client invocation executes server-side code with the operator's stored Atlassian credentials. The vulnerability is CWE-22 (Improper Limitation of a Pathname to a Restricted Directory / Path Traversal) rooted in the Confluence attachment upload path: in src/mcp_atlassian/confluence/attachments.py, upload_attachment() normalised a caller-supplied file_path with os.path.abspath() when it was not already absolute, but never validated it against the workspace. Because absolute paths pass through unchanged and traversal sequences resolve outside the working directory, a caller-controlled file_path becomes an arbitrary local file read whose contents are then pushed to Confluence as an attachment - effectively an exfiltration primitive. The upstream fix replaces the abspath() call with validate_safe_path(file_path), confining the upload source to the workspace. This CVE is explicitly a follow-on to CVE-2026-27825: that earlier remediation constrained download destinations but the same class of untrusted path input remained unvalidated on the upload side. The accompanying PR #1448 bundles further related hardening - DNS pinning and SSRF redirect validation on the Confluence session, an AND-only spaces allowlist so a caller-supplied spaces_filter can no longer widen an operator's configured space boundary in shared-credential deployments, and a refusal to write downloads into the working-directory root to prevent overwriting importable Python modules (GHSA-6vmq) - which indicates the maintainers treated caller-supplied path and scope inputs across the server as a systemic trust boundary issue. Per the assessed vector AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N, the attack is network-reachable with low complexity and requires only the low-privileged ability to invoke the tool, with high confidentiality impact and no integrity or availability effect.

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-facing MCP server, low complexity; PR:L because a permitted caller with tool access is required; confidentiality-only via arbitrary file read, no integrity/availability impact and no scope change.

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 - 20:18 EUVD

DescriptionCVE.org

MCP Atlassian is a Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Prior to 0.22.0, the remediation for CVE-2026-27825 protects download destinations but does not constrain source paths used by attachment uploads. A caller can provide an absolute or traversal file_path and cause the server to upload the selected local file. The advisory traces the vulnerable input and processing flow through upload_attachment, file_path, and CVE-2026-27825, 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 Python MCP server for Atlassian, limited production footprint
Threat Intel
1
1 source
Exploit
POC
Public exploit code exists
Data Quality
5 sources
Confidence: Medium

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· derived
Poc
System Exposure· derived
Open
Automatable· derived
No
Human Impact· derived
Medium

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