dbcve.org
Server-Side Request Forgery (SSRF)Weakness · CWE-918

CVE-2026-56663

HIGH · 8.5 CVSS v3.1 Published 2026-06-26
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
91/100
Remediation priority · Urgent
Remotely reachable Zero-click 8 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

The vulnerability exists in _is_ip_blocked() within backend/backend/util/request.py. The function fails to normalize IPv4-mapped IPv6 addresses (e.g., ::ffff:192.168.1.1) to their IPv4 equivalents before checking against blocked ranges, and also omits blocking the 100.64.0.0/10 (CGNAT) range per RFC 6598. This allows authenticated users to bypass SSRF protections and access internal network services.

MitigationUpgrade AutoGPT Platform to version 0.6.52 or later, which implements proper IPv4-mapped IPv6 address normalization and adds blocking for the RFC 6598 special-use range.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
High
Privileges
Low
User interaction
None
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Check installed AutoGPT version
    Run 'git describe --tags' in the repository directory, or inspect pyproject.toml, setup.py, or a version file to determine the current version number
    Affected if Version is 0.6.51 or earlier (before the 0.6.52 fix)
  2. Locate the _is_ip_blocked function
    Search the codebase for the _is_ip_blocked function definition within SendWebRequestBlock (typically in a blocks or requests module)
    Affected if Function exists and is being used for SSRF protection checks
  3. Inspect IPv4-mapped IPv6 handling
    Examine the _is_ip_blocked function source code to see if it normalizes IPv4-mapped IPv6 addresses (::ffff:x.x.x.x format) to IPv4 before applying blocked range checks
    Affected if No normalization code for IPv4-mapped IPv6 addresses is present before the IP range comparison
  4. Verify CGNAT range blocking
    Search the blocked IP ranges configuration or hardcoded list within the _is_ip_blocked function for the 100.64.0.0/10 CIDR range (RFC 6598)
    Affected if The 100.64.0.0/10 range is not included in the blocked IP list

Environment is affected if running AutoGPT version 0.6.51 or earlier AND the _is_ip_blocked function lacks IPv4-mapped IPv6 address normalization AND does not block the 100.64.0.0/10 CGNAT range.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade AutoGPT Platform to version 0.6.52 or later, which implements proper IPv4-mapped IPv6 address normalization and adds blocking for the RFC 6598 special-use range.

Recommended fix High confidence

0.6.52

  1. Check current installed version of AutoGPT Platform using the platform's version command or admin interface
  2. Upgrade AutoGPT Platform to version 0.6.52 or later
  3. Verify the upgrade was successful by confirming the new version number
  4. Test that the SendWebRequestBlock properly blocks IPv4-mapped IPv6 addresses and special-use ranges like 100.64.0.0/10

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation2.0 h
  • Implementation4.0 h
  • Testing6.0 h
  • Review / QA3.0 h
15.0 hours of engineering $2,560
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,096.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-56663 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-56663 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data