Cloudflare Agents up to 0.3.9 server.ts error_description cross site scripting

Summaryinfo

A vulnerability, which was classified as problematic, has been found in Cloudflare Agents up to 0.3.9. This impacts an unknown function of the file site/ai-playground/src/server.ts. This manipulation of the argument error_description causes cross site scripting. This vulnerability is handled as CVE-2026-1721. The attack can be initiated remotely. There is not any exploit available. It is advisable to upgrade the affected component.

Detailsinfo

A vulnerability classified as problematic was found in Cloudflare Agents up to 0.3.9. Affected by this vulnerability is an unknown functionality of the file site/ai-playground/src/server.ts. The manipulation of the argument error_description with an unknown input leads to a cross site scripting vulnerability. The CWE definition for the vulnerability is 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. As an impact it is known to affect integrity. The summary by CVE is:

Summary A Reflected Cross-Site Scripting (XSS) vulnerability was discovered in the AI Playground's OAuth callback handler. The `error_description` query parameter was directly interpolated into an HTML script tag without proper escaping, allowing attackers to execute arbitrary JavaScript in the context of the victim's session. Root cause The OAuth callback handler in `site/ai-playground/src/server.ts` directly interpolated the `authError` value, sourced from the `error_description` query parameter, into an inline `<script>` tag. Impact An attacker could craft a malicious link that, when clicked by a victim, would: * Steal user chat message history - Access all LLM interactions stored in the user's session. * Access connected MCP Servers - Interact with any MCP servers connected to the victim's session (public or authenticated/private), potentially allowing the attacker to perform actions on the victim's behalf Mitigation: * PR:  https://github.com/cloudflare/agents/pull/841 https://github.com/cloudflare/agents/pull/841 * Agents-sdk users should upgrade to [email protected] * Developers using configureOAuthCallback with custom error handling in their own applications should ensure all user-controlled input is escaped before interpolation.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-1721 since 01/30/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. It demands that the victim is doing some kind of user interaction. Technical details of the vulnerability are known, but there is no available exploit. The attack technique deployed by this issue is T1059.007 according to MITRE ATT&CK.

Upgrading to version 0.3.10 eliminates this vulnerability. Applying a patch is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

The vulnerability is also documented in the vulnerability database at CNNVD (CNNVD-202602-2314). Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Type

• Cloud Software

Vendor

• Cloudflare

Name

• Agents

Version

• 0.3.0
• 0.3.1
• 0.3.2
• 0.3.3
• 0.3.4
• 0.3.5
• 0.3.6
• 0.3.7
• 0.3.8
• 0.3.9

Website

• Product: https://github.com/cloudflare/agents/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Be aware that VulDB is the high quality source for vulnerability data.

Discussion