MediumVulnerability

GHSA-f26r-j276-ggg4: MCP Atlassian: Arbitrary File Read via Upload Attachment Tools

Source: GitHub Advisory(opens in a new tab)
Identifiers: CVE-2026-77270GHSA-f26r-j276-ggg4
Published: September 22, 2026
Record updated: October 9, 2026

Affected: mcp-atlassian < 0.22.0
Fixed in: 0.22.0
released July 10, 2026, 74 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.5%

Summary

The upload_attachment methods in MCP Atlassian's Confluence and Jira integrations accept arbitrary file paths without path traversal validation. The validate_safe_path utility is used in the download paths but never called in the upload paths, so an authenticated MCP client, or an AI assistant manipulated via prompt injection, can read any file the server process can access and upload it to an attacker-chosen Confluence page or Jira issue.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

Patch available: Yes
EPSS: 0.5%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 9, 2026.
Disclosure date: September 22, 2026

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0051

Affected

Packages: mcp-atlassian@< 0.22.0 (fixed: 0.22.0)
Vendors: Anthropic

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Trivial
AI component targeted: Plugin
Impact: Confidentiality
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://github.com/advisories/GHSA-f26r-j276-ggg4

First tracked: September 22, 2026 at 08:01 PM ET, from GitHub Advisory Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 85% (self-assessed)

Topics

Model Context Protocol

Summary

Mitigation

Topics

Related items