CVE-2026-56663: AutoGPT: SSRF-to-RCE Chain in `SendWebRequestBlock` via IP validation bypass and internal `pg-meta` access

Published Jun 26, 2026
·
Updated

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.52, an authenticated user can bypass the SSRF / private-IP protections in SendWebRequestBlock and reach internal network services. isipblocked() in backend/backend/util/request.py does not normalize IPv4-mapped IPv6 addresses before checking resolved IPs against the blocked IPv4 ranges, and does not block special-use ranges such as 100.64.0.0/10 (CGNAT, RFC 6598). A hostname that resolves to an IPv4-mapped IPv6 address therefore passes validation and the request reaches the embedded internal IPv4 endpoint. This affects all AutoGPT Platform deployments. This vulnerability is fixed in 0.6.52.

Affected Software

1 affected component
AutoGPT<0.6.52

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade AutoGPT Platform to a version that resolves this vulnerability.

    Fixed in 0.6.52
  2. Configuration

    Ensure _is_ip_blocked() normalizes IPv4-mapped IPv6 addresses prior to comparing resolved IPs to the blocked IPv4 ranges, and that the blocked ranges include special-use networks such as 100.64.0.0/10 (CGNAT, RFC 6598).

    AutoGPT backend/backend/util/request.py (SendWebRequestBlock / _is_ip_blocked) IP validation must normalize IPv4-mapped IPv6 addresses before checking resolved IPs against blocked IPv4 ranges, and must block special-use ranges such as 100.64.0.0/10 (CGNAT, RFC 6598) = normalize IPv4-mapped IPv6 before range checks; block 100.64.0.0/10

Event History

Jun 26, 2026
CVE Published
via MITRE·04:04 PM
Data Sourced
via MITRE·04:04 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·05:16 PM
DescriptionSeverityWeakness
Free Weekly Intel

Don't miss critical vulnerabilities

Join thousands of security professionals who receive our weekly digest of trending CVEs, zero-days, and exploited vulnerabilities.

No spam. Unsubscribe anytime.

Frequently Asked Questions

1

What is the severity of CVE-2026-56663?

The severity of CVE-2026-56663 is rated as high with a score of 8.5.

2

How do I fix CVE-2026-56663?

To fix CVE-2026-56663, upgrade to AutoGPT version 0.6.52 or later.

3

What is the risk associated with CVE-2026-56663?

CVE-2026-56663 poses a risk level of 73, indicating significant potential impact.

4

What type of vulnerability is CVE-2026-56663?

CVE-2026-56663 is classified as a Server-Side Request Forgery (SSRF) vulnerability.

5

What can an attacker achieve with CVE-2026-56663?

An attacker can exploit CVE-2026-56663 to bypass IP validation and access internal network services.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203