CVE-2026-56663

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

Published Jun 26, 2026 CVSS 3.1 · 8.5 High EPSS < 1% KEV · Not listed
Description
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. _is_ip_blocked() 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.

Analysis

AI-generated

Technical impact

The vulnerability resides in the SendWebRequestBlock component of the AutoGPT Platform. An authenticated user can supply an IPv4‑mapped IPv6 address that bypasses the backend’s IP validation, allowing a request to reach internal network services. This SSRF bypass can be chained to internal endpoints and potentially result in remote code execution. The weakness is classified as CWE‑918.

Affected Systems

All deployments of Significant‑Gravitas AutoGPT Platform running a version prior to 0.6.52 are affected, encompassing every instance that has not applied the 0.6.52 update.

Risk and Exploitability

With a CVSS score of 8.5 the flaw is high severity, and the EPSS score is not available. The vulnerability is not listed in CISA KEV, but it requires authenticated access and operates over the internal network, making it a serious risk if exploited. An attacker with platform credentials can trigger the SSRF and reach internal services, potentially leading to code execution.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade the AutoGPT Platform to version 0.6.52 or later to apply the fixed IP validation logic.
  • As a temporary patch, configure the backend or network firewall to reject IPv4‑mapped IPv6 addresses and special‑use IP ranges such as 100.64.0.0/10, blocking SSRF attempts.
  • Enforce strict role‑based access control on the SendWebRequestBlock API and enable audit logging to detect and prevent unauthorized use.

Generated by OpenCVE AI on June 26, 2026 at 18:35 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
First Time appeared Significant-gravitas
Significant-gravitas autogpt
Vendors & Products Significant-gravitas
Significant-gravitas autogpt
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
Description 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. _is_ip_blocked() 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.
Title AutoGPT: SSRF-to-RCE Chain in `SendWebRequestBlock` via IP validation bypass and internal `pg-meta` access
Weaknesses CWE-918
References
Metrics cvssV3_1

{'score': 8.5, 'vector': 'CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H'}

Weaknesses
  • CWE-918

    Server-Side Request Forgery (SSRF)

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Jun 26, 2026, 6:13 PM
Reserved
Jun 22, 2026, 4:39 PM
Status
Deferred
Published
Jun 26, 2026, 5:16 PM
Modified
Oct 25, 2026, 5:10 PM