dbcve.org
Uncontrolled Resource ConsumptionWeakness · CWE-400

CVE-2025-32437

HIGH · 8.7 CVSS v4.0 Published 2026-06-18
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
96/100
Remediation priority · Urgent
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 workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, `MediaDurationBlock` will download and store the video in a temporary directory without deleting before all noded are done. `StepThroughItemsBlock` can be used to iterate `MediaDurationBlock` multiple times. `StepThroughItemsBlock` does not limit the number of loops. In addition, `MediaDurationBlock ` does not limit the amount of disk space consumed in the current working directory and does not delete the video after outputing the result. When a malicious user chooses to screen shot many web pages, the disk space will eventually run out, causing a DoS. Version 0.6.63 patches the issue.

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 before 0.6.63 has a denial-of-service vulnerability where MediaDurationBlock downloads videos to a temp directory without cleanup, and StepThroughItemsBlock allows unlimited iteration. Combined, these enable an attacker to exhaust disk space by iterating many web page screenshots.

MitigationUpgrade to AutoGPT version 0.6.63 or later, which adds proper file cleanup and iteration limits.

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
Low
Privileges
None
Authentication
X
User interaction
None
Scope
X

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

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. Identify installed AutoGPT version
    Locate the AutoGPT package or source directory and read the version file, or run 'pip show autogpt' or check the version indicated in your deployment
    Affected if The version is below 0.6.63 (e.g., 0.6.0, 0.5.2, etc.)
  2. Check for MediaDurationBlock usage
    Search project logs, configuration, or blocks directory for instances of 'MediaDurationBlock' being invoked, which downloads videos to a temp location
    Affected if MediaDurationBlock is actively used in any workflow or pipeline
  3. Check for StepThroughItemsBlock usage
    Search project logs, configuration, or blocks directory for instances of 'StepThroughItemsBlock' which handles iteration over items
    Affected if StepThroughItemsBlock is actively used in any workflow or pipeline, particularly with image or web content
  4. Inspect temp directory storage behavior
    Monitor the system's temporary directory (usually /tmp or OS-specific temp folder) while AutoGPT runs a task involving video or image processing
    Affected if Temp files accumulate and are not cleaned up after task completion, or disk usage grows unexpectedly during AutoGPT operations
  5. Verify iteration configuration limits
    Review AutoGPT configuration files or settings for any iteration limits applied to StepThroughItemsBlock
    Affected if No iteration limits are configured, or limits are set to unlimited/unrestricted

You are affected if running AutoGPT version 0.6.63 or earlier AND using MediaDurationBlock or StepThroughItemsBlock in workflows, with unchecked temp file accumulation and unlimited iteration enabled.

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 to AutoGPT version 0.6.63 or later, which adds proper file cleanup and iteration limits.

Recommended fix High confidence

AutoGPT version 0.6.63

  1. 1. Identify the current AutoGPT installation method (e.g., pip install, Docker, or source)
  2. 2. For pip installations: Run 'pip install --upgrade autogpt' to upgrade to the latest version which includes 0.6.63
  3. 3. For Docker installations: Pull the latest image or specify version 0.6.63: 'docker pull autogpt/autogpt:0.6.63' or update your docker-compose.yml
  4. 4. For source installations: Navigate to the AutoGPT repository and run 'git fetch origin' followed by 'git checkout 0.6.63' or 'git pull' to get the fixed version
  5. 5. After upgrading, verify the version by checking 'autogpt --version' or inspecting the package metadata
  6. 6. Restart any running AutoGPT services to ensure the patched version is active

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
  • Testing2.0 h
  • Review / QA1.0 h
9.0 hours of engineering $1,600
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,560.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2025-32437 — 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-2025-32437 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