CVE-2025-32436: CWE-400: Uncontrolled Resource Consumption in Significant-Gravitas AutoGPT
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, `AddAudioToVideoBlock` will download and store the video and audio 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, `AddAudioToVideoBlock` 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.
AI Analysis
Technical Summary
AutoGPT versions before 0.6.63 contain a resource exhaustion vulnerability (CWE-400) where the AddAudioToVideoBlock downloads and stores video and audio files in a temporary directory without deleting them after processing, and does not limit disk space usage. Additionally, StepThroughItemsBlock can iterate MediaDurationBlock an unlimited number of times, allowing a malicious user to cause excessive disk consumption by repeatedly processing media, eventually leading to a denial of service due to disk space exhaustion. This vulnerability is patched in version 0.6.63.
Potential Impact
An attacker with limited privileges can exploit this vulnerability by triggering repeated media processing operations that consume disk space without cleanup, leading to exhaustion of available disk resources. This results in a denial of service condition, potentially disrupting the availability of the AutoGPT platform.
Mitigation Recommendations
Upgrade to AutoGPT version 0.6.63 or later, where the issue is patched. There is no official fix or temporary workaround indicated other than applying this update. Since this is not a cloud service, remediation depends on user action to update the software.
CVE-2025-32436: CWE-400: Uncontrolled Resource Consumption in Significant-Gravitas AutoGPT
Description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.63, `AddAudioToVideoBlock` will download and store the video and audio 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, `AddAudioToVideoBlock` 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.
CVSS v4.0
Score 7.1high
Affected software
pkg:github/significant-gravitas/AutoGPTRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
AutoGPT versions before 0.6.63 contain a resource exhaustion vulnerability (CWE-400) where the AddAudioToVideoBlock downloads and stores video and audio files in a temporary directory without deleting them after processing, and does not limit disk space usage. Additionally, StepThroughItemsBlock can iterate MediaDurationBlock an unlimited number of times, allowing a malicious user to cause excessive disk consumption by repeatedly processing media, eventually leading to a denial of service due to disk space exhaustion. This vulnerability is patched in version 0.6.63.
Potential Impact
An attacker with limited privileges can exploit this vulnerability by triggering repeated media processing operations that consume disk space without cleanup, leading to exhaustion of available disk resources. This results in a denial of service condition, potentially disrupting the availability of the AutoGPT platform.
Mitigation Recommendations
Upgrade to AutoGPT version 0.6.63 or later, where the issue is patched. There is no official fix or temporary workaround indicated other than applying this update. Since this is not a cloud service, remediation depends on user action to update the software.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2025-04-08T10:54:58.368Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a341e7df198dc38c11fcd35
Added to database: 6/18/2026, 4:36:13 PM
Last enriched: 6/18/2026, 4:50:23 PM
Last updated: 6/19/2026, 5:21:24 AM
Views: 8
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.