LiveActive security incident?Get immediate response
CVE Record

CVE-2026-1721: Reflected Cross-Site Scripting (XSS) vulnerability in AI Playground site

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.

MediumCVSS 6.2Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysismoderate

Security readout for executives and security teams

Plain-English summary

CVE-2026-1721 is a reflected XSS issue in Cloudflare’s AI Playground OAuth callback handling. A victim must click a crafted link. If successful, attacker-controlled JavaScript could run in the victim’s session, exposing chat history and connected MCP server access. The vendor-linked mitigation is to upgrade agents-sdk users to agents@0.3.10.

Executive priority

Treat as a timely remediation item for affected AI Playground or agents-sdk deployments. Business risk centers on session data exposure and possible actions through connected MCP servers, but exploitation requires user interaction and active exploitation is not reported in the provided sources.

Technical view

The OAuth callback handler interpolated the error_description query parameter into an inline script without proper escaping, causing CWE-79 reflected XSS. CVSS v4.0 is 6.2. The advisory names the agents package and custom uses of configureOAuthCallback with error handling as areas to review.

Likely exposure

Exposure is most likely for deployments using the AI Playground site or agents-sdk OAuth callback functionality, especially custom configureOAuthCallback error handling. The CVE record lists agents and states the default status is unaffected, so confirm actual dependency and code usage.

Exploitation context

The source describes user interaction as required: a victim clicks a malicious link. The CVE is not listed as CISA KEV in the provided data, and no cited source states active exploitation.

Researcher notes

Evidence is limited to the CVE record and linked GitHub PR. The root cause and impact are clearly described, but affected version ranges are sparse. Validate by dependency inventory and source review rather than assuming all agents users are affected.

Mitigation direction

  • Upgrade agents-sdk users to agents@0.3.10.
  • Review custom configureOAuthCallback error handling for unsafe interpolation.
  • Escape all user-controlled input before inserting it into HTML or scripts.
  • Check the GitHub PR and vendor guidance for implementation details.

Validation and detection

  • Inventory applications using the agents package or AI Playground code.
  • Confirm deployed agents version is 0.3.10 or later where applicable.
  • Review OAuth callback code paths using error_description or authError.
  • Verify user-controlled values are escaped before HTML/script rendering.
  • Check security monitoring for suspicious OAuth callback error patterns.
Prepared
Confidence
medium
Sources
3

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · medium confidence lookup

CWE-79: User-session and phishing behavior lookup

Client-side and session-facing weaknesses should be reviewed alongside initial-access and user-execution behaviors. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-1721 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
Medium
CVSS
6.2 (4.0)
Known Exploited
No
Published

Vector: 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

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

1CVSS vectors
0Timeline events
0ADP providers
2Source links

CVSS vector scores

1 official score

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
6.2CVSS 4.0MediumCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:N/VI:N/VA:N/SC:H/SI:L/SA:N——Primary CVE score

Vulnerability scoring details

Base CVSS 4.0 score

6.2Medium
CVSS 4.0 vector shape for CVE-2026-1721Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

Vector: 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

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
Unknown vendoragentsagents, 0unaffected
Weakness

CWE details

CWE-79

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-79 · source CWE mapping

Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting')

Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs