Monitor vulnerabilities like this one.
Sign up free to get alerted when software you use is affected.
6.2
Cloudflare Agents: Malicious Links Can Steal User Chat History
GHSA-w5cr-2qhr-jqc5
Summary
A security issue in Cloudflare Agents' AI Playground site allows attackers to create malicious links that steal user chat history and access sensitive information. To fix this, update to Cloudflare Agents 0.3.10 or ensure custom error handling properly escapes user input. This is a critical update to protect user data and prevent unauthorized access.
What to do
- Update GitHub Actions agents to version 0.3.10.
Affected software
| Vendor | Product | Affected versions | Fix available |
|---|---|---|---|
| GitHub Actions | agents | <= 0.3.10 | 0.3.10 |
Original title
Cloudflare Agents has a Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site
Original 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
- 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.
### Credits
Disclosed responsibly by Nishant Kumawat
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
- 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.
### Credits
Disclosed responsibly by Nishant Kumawat
ghsa CVSS4.0
6.2
Vulnerability type
CWE-79
Cross-site Scripting (XSS)
Published: 13 Feb 2026 · Updated: 7 Mar 2026 · First seen: 6 Mar 2026