Autogpt PlatformApplication · Agpt

CVE-2025-62615

CRITICAL · 9.8 CVSS v3.1 Published 2026-02-04
Fix available
A fix is available. Upgrade to 0.6.34 or later.
See remediation →
100/100
Remediation priority · Urgent
Public exploit Remotely reachable No privileges Zero-click

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 platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in RSSFeedBlock, the third-party library urllib.request.urlopen is used directly to access the URL, but the input URL is not filtered, which will cause SSRF vulnerability. This issue has been patched in autogpt-platform-beta-v0.6.34.

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

AutoGPT's RSSFeedBlock component uses urllib.request.urlopen to fetch URLs from user input without any sanitization or validation, allowing attackers to make the server perform requests to internal resources or external malicious targets. This Server-Side Request Forgery (SSRF) vulnerability has a critical CVSS score of 9.8 due to the ease of exploitation and potential for complete system compromise through internal network pivoting.

MitigationUpgrade to autogpt-platform-beta-v0.6.34 or later. If upgrading is not immediately possible, implement URL allowlist validation and restrict urllib.request.urlopen to trusted domains only.

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

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
Autogpt PlatformApplication
Affected:< 0.6.34

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
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/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 the installed AutoGPT platform version
    Run 'pip show autogpt-platform' or check your package manager for the installed version of autogpt-platform or autogpt-platform-beta
    Affected if The installed version is lower than 0.6.34
  2. Locate the RSSFeedBlock implementation
    Search the codebase for files containing 'RSSFeedBlock' - typically in blocks or plugins directory
    Affected if RSSFeedBlock code exists in the environment
  3. Inspect RSSFeedBlock for urllib.request.urlopen usage
    Open the RSSFeedBlock source file and search for 'urllib.request.urlopen' calls without validation logic
    Affected if The code uses urllib.request.urlopen to fetch URLs without input validation or allowlist checking
  4. Verify if URL validation is implemented
    Search for URL validation patterns such as 'urllib.parse' checks, allowlists, or blocklists in the RSSFeedBlock file
    Affected if No URL validation, allowlist, or blocklist is present in the RSSFeedBlock code
  5. Confirm RSSFeedBlock is actively configured or used
    Check configuration files, database, or runtime settings for active RSSFeedBlock instances or feeds
    Affected if RSSFeedBlock is enabled or configured with user-controlled URLs

You are affected if the AutoGPT platform version is below 0.6.34 AND the RSSFeedBlock is in use with unvalidated URL input.

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
Upgrade available Upgrade to 0.6.34 or later
Fixed in 0.6.34
Interim mitigation

Upgrade to autogpt-platform-beta-v0.6.34 or later. If upgrading is not immediately possible, implement URL allowlist validation and restrict urllib.request.urlopen to trusted domains only.

Recommended fix High confidence

autogpt-platform-beta-v0.6.34

  1. Upgrade AutoGPT Platform to version autogpt-platform-beta-v0.6.34 or later

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

Fix this in Autogpt Platform Scoped from the published advisory
  • Consultation2.0 h
  • Implementation4.0 h
  • Testing3.0 h
  • Review / QA1.0 h
10.0 hours of engineering $1,750
Get the upgrade done

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,800.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-62615 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

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-2025-62615 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