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 agents@0.3.10
* Developers using configureOAuthCallback with custom error handling in their own applications should ensure all user-controlled input is escaped before interpolation.
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| unaffected |
|
No data.
No data.
No data.
Project Subscriptions
No data.
No advisories yet.
Solution
* PR: https://github.com/cloudflare/agents/pull/841 https://github.com/cloudflare/agents/pull/841 * Agents-sdk users should upgrade to `agents@0.3.10` * Developers using `configureOAuthCallback` with custom error handling in their own applications should ensure all user-controlled input is escaped before interpolation.
Workaround
No workaround given by the vendor.
| Link | Providers |
|---|---|
| https://github.com/cloudflare/agents/pull/841 |
|
Fri, 13 Feb 2026 02:30:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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: https://github.com/cloudflare/agents/pull/841 https://github.com/cloudflare/agents/pull/841 * Agents-sdk users should upgrade to agents@0.3.10 * Developers using configureOAuthCallback with custom error handling in their own applications should ensure all user-controlled input is escaped before interpolation. | |
| Title | Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site | |
| References |
| |
| Metrics |
cvssV4_0
|
Projects
Sign in to view the affected projects.
MITRE
Status: PUBLISHED
Assigner: cloudflare
Published:
Updated: 2026-02-13T01:48:24.571Z
Reserved: 2026-01-30T20:12:22.668Z
Link: CVE-2026-1721
Vulnrichment
No data.
NVD
Status : Received
Published: 2026-02-13T03:15:52.467
Modified: 2026-02-13T03:15:52.467
Link: CVE-2026-1721
Redhat
No data.
OpenCVE Enrichment
No data.
No weakness.