CVE-2026-26993
Stored XSS in Flare File Sharing via Unsanitized SVG Uploads
Publication date: 2026-02-20
Last updated on: 2026-03-03
Assigner: GitHub, Inc.
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| flintsh | flare | to 1.7.1 (exc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-79 | The product does not neutralize or incorrectly neutralizes user-controllable input before it is placed in output that is used as a web page that is served to other users. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
[{'type': 'paragraph', 'content': 'CVE-2026-26993 is a stored Cross-Site Scripting (XSS) vulnerability in the FlintSH/Flare application, a Next.js-based file sharing platform. Versions 1.7.0 and below allow users to upload files without proper content validation or sanitization. Attackers can embed malicious JavaScript within SVG files or other active content formats like HTML or XML. When a victim views the uploaded file in "raw" mode, the malicious script executes in the context of the application\'s origin.'}, {'type': 'paragraph', 'content': 'This script execution can be used by attackers to exfiltrate sensitive user data such as localStorage, sessionStorage, and cookies to an attacker-controlled server.'}] [1]
How can this vulnerability impact me? :
This vulnerability can impact users by allowing attackers to steal sensitive information such as session tokens and other data stored in the browser. It compromises visitors who access shared content, even if they do not have an account on the platform.
Attackers can perform actions on behalf of authenticated users by exploiting the stolen credentials or session information, potentially leading to unauthorized access or data breaches.
The vulnerability has a moderate severity with a CVSS v3.1 base score of 4.6, indicating a network attack vector with low attack complexity and requiring user interaction.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
I don't know
How can this vulnerability be detected on my network or system? Can you suggest some commands?
[{'type': 'paragraph', 'content': 'This vulnerability can be detected by checking if your FlintSH/Flare installation is running a version prior to 1.7.1, as versions 1.7.0 and below are vulnerable.'}, {'type': 'paragraph', 'content': 'You can also detect attempts to exploit this vulnerability by monitoring for uploads of SVG or other active content files (HTML, XML) that contain embedded JavaScript payloads.'}, {'type': 'paragraph', 'content': 'Since the exploit involves viewing files in βrawβ mode, monitoring HTTP requests to the /raw file viewer endpoint for suspicious file types or unusual parameters may help detect exploitation attempts.'}, {'type': 'paragraph', 'content': 'Suggested commands to detect vulnerable versions or suspicious activity include:'}, {'type': 'list_item', 'content': 'Check the installed version of Flare: `flare --version` or check the version in your deployment manifest or Docker image tags.'}, {'type': 'list_item', 'content': "Search logs for uploads of SVG or HTML files containing <script> tags or suspicious JavaScript code, e.g., using grep: `grep -i '<script' /path/to/flare/uploads/*`"}, {'type': 'list_item', 'content': "Monitor HTTP access logs for requests to the raw file viewer endpoint, e.g., `grep '/raw/' /var/log/nginx/access.log` and analyze for unusual patterns."}] [1]
What immediate steps should I take to mitigate this vulnerability?
The immediate and most effective mitigation is to upgrade your FlintSH/Flare installation to version 1.7.1 or later, where this vulnerability has been fixed.
The patch includes adding security HTTP headers such as Content-Security-Policy with sandboxing and X-Content-Type-Options to prevent script execution and MIME-type confusion.
If upgrading immediately is not possible, consider restricting or disabling the ability to upload SVG, HTML, or XML files until the patch can be applied.
Additionally, monitor and audit file uploads and access to the raw file viewer to detect and block potential exploitation attempts.