6.2
/ 10
MEDIUM
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:N/VI:N/VA:N/SC:H/SI:L/SA:N
Description
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:Β https://github.com/cloudflare/agents/pull/841 https://github.com/cloudflare/agents/pull/841
* Agents-sdk users should upgrade toΒ [email protected]
* Developers using configureOAuthCallback with custom error handling in their own applications should ensure all user-controlled input is escaped before interpolation.
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:Β https://github.com/cloudflare/agents/pull/841 https://github.com/cloudflare/agents/pull/841
* Agents-sdk users should upgrade toΒ [email protected]
* Developers using configureOAuthCallback with custom error handling in their own applications should ensure all user-controlled input is escaped before interpolation.
Basic Information
ID
CVE-2026-1721
Source
cloudflare
Published
Feb 13, 2026 at 01:46
Modified
Feb 13, 2026 at 01:48
Affected Product
Affected Versions
0