Skip to content
cloudflare-agentsGHSA-cvhv-6xm6-c3v4

Cloudflare Agents is Vulnerable to Reflected Cross-Site Scripting in the AI Playground's OAuth callback handler

MediumCVE-2026-1721 · Published Feb 13, 2026

GitHub advisory

Affected versions

PackageAffectedFixed in
agents
npm
< 0.3.100.3.10
Details and references

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.

CVSS 4.0
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
Severity from
GitHub (reviewed advisory)
Weakness
CWE-79
Also known as
CVE-2026-1721

More cloudflare-agents advisories

All
DateAdvisory
Feb 13Cloudflare Agents has a Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site
GHSA-w5cr-2qhr-jqc5Mediumfixed in 0.3.10
Feb 3Cloudflare Agents SDK has Insecure Direct Object Reference (IDOR) via Header-Based Email Routing
CVE-2026-1664Mediumfixed in 0.3.7

Critical advisories by email

Wednesdays: the week’s critical and high advisories in the AI and data stack, with the fixed versions. Only in weeks that have some.

Double opt-in. Unsubscribe any time.