Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:LSummary
CVE-2026-55237 is a high-severity Improper Neutralization of Alternate XSS Syntax (CWE-87) vulnerability. Its CVSS base score is 8.8 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Content Injection (T1659); ranked at the 24th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as LLM Application Platforms.
The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-37915
Vulnerability Data
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions prior to 0.6.62 have a DOM-based Cross-Site Scripting (XSS) vulnerability in AutoGPT's signup page. The application improperly trusts a URL parameter (`next`), which is…
more
passed to `router.push`. An attacker can craft a malicious link that, when opened by an authenticated user, performs a client-side redirect and executes arbitrary JavaScript in the context of their browser. This could lead to credential theft, internal network pivoting, and unauthorized actions performed on behalf of the victim. Version 0.6.62 patches the issue.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- N/A
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: artificial intelligence
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V3.7.2
Mitigating Controls (NIST 800-53 r5) AI
SA-11 requires developer testing and analysis that can discover improper neutralization of alternate script syntax after it has been coded.
SI-10 directly requires validation/sanitization of untrusted inputs, which structurally stops alternate XSS syntax from reaching the interpreter.
Information flow enforcement can restrict redirects to only approved/trusted destinations, stopping untrusted user-supplied URLs from being followed.
SA-8 mandates secure engineering principles such as input neutralization and output encoding that prevent introduction of this class of flaw.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly require proper input neutralization and output encoding to prevent alternate XSS syntax.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Secure coding standards require proper neutralization of alternate script syntax, directly eliminating CWE-87.
Security testing catches residual XSS but does not itself implement the neutralization controls.
Preventing access to attacker-controlled or malicious sites stops users from being redirected to untrusted locations via open-redirect or phishing links.
Secure SDLC mandates input validation and output encoding that directly prevent alternate XSS syntax.
Application security requirements explicitly call for neutralization of untrusted input to block XSS variants.
Secure architecture principles reduce attack surface but do not prescribe specific encoding rules.