PatchSiren cyber security CVE debrief
CVE-2025-32436 Significant-Gravitas CVE debrief
CVE-2025-32436 AutoGPT Denial of Service Vulnerability. AutoGPT, a workflow automation platform, contains a high-severity vulnerability (CVE-2025-32436) that can cause a denial of service (DoS) due to excessive disk space consumption. The vulnerability exists in the `AddAudioToVideoBlock` and `StepThroughItemsBlock` components. Defenders responsible for AutoGPT deployments should assess exposure and prioritize remediation by updating to version 0.6.63 or later, monitoring disk space usage, and implementing input validation and sanitization. This vulnerability allows malicious users to consume excessive disk space by exploiting the components, potentially leading to a DoS. To remedi
- Vendor
- Significant-Gravitas
- Product
- AutoGPT
- CVSS
- HIGH 7.1
- CISA KEV
- Not listed in stored evidence
- Original CVE published
- 2026-06-18
- Original CVE updated
- 2026-09-29
- Advisory published
- 2026-06-18
- Advisory updated
- 2026-09-29
Who should care
Defenders responsible for AutoGPT deployments should assess exposure and prioritize remediation. System administrators and security teams should review and update AutoGPT to version 0.6.63 or later, monitor disk space usage, and implement input validation and sanitization for user-provided data.
Why it matters
CVE-2025-32436 is a high-severity vulnerability in AutoGPT that can cause a denial of service (DoS) due to excessive disk space consumption. Defenders responsible for AutoGPT deployments should assess exposure and prioritize remediation by updating to version 0.6.63 or later, monitoring disk space usage, and implementing input validation and sanitization.
- Potential denial of service (DoS) due to excessive disk space consumption
- Need to verify and update AutoGPT to version 0.6.63 or later
- Requirement to monitor disk space usage and implement limits
- Importance of input validation and sanitization for user-provided data
Technical summary
The vulnerability exists in the `AddAudioToVideoBlock` and `StepThroughItemsBlock` components of AutoGPT. The `AddAudioToVideoBlock` downloads and stores videos and audio in a temporary directory without deleting them after use. The `StepThroughItemsBlock` can be used to iterate `MediaDurationBlock` multiple times without limiting the number of loops. This can cause excessive disk space consumption, leading to a denial of service (DoS).
Defensive priority
High
Recommended defensive actions
- Review and update AutoGPT to version 0.6.63 or later
- Monitor disk space usage and implement limits
- Implement input validation and sanitization for user-provided data
- Confirm whether affected AutoGPT deployments exist in managed environments and assign an owner for follow-up
- Review compensating controls for exposed AutoGPT systems while remediation is scheduled and verified
- Check relevant monitoring, detection, and logs for exposed AutoGPT assets that need extra review
- Track exceptions, retest remediated AutoGPT assets, and close the item only after evidence is documented
Evidence notes
The CVE record and NVD entry provide details on the vulnerability in AutoGPT, a workflow automation platform. The vulnerability exists in the `AddAudioToVideoBlock` and `StepThroughItemsBlock` components, which can be exploited to cause a denial of service (DoS) by consuming excessive disk space.
Sources and references
Verified primary and authoritative sources
-
CVE-2025-32436 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2025-32436
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2025-32436 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2025-32436
NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.
Supplemental references
-
Source reference
Unverified legacy reference
URL: https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-g26x-xwc5-7p44
Methodology and review provenance
AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.