PatchSiren cyber security CVE debrief
CVE-2025-32437 Significant-Gravitas CVE debrief
CVE-2025-32437 AutoGPT Denial of Service Vulnerability. AutoGPT, a workflow automation platform, contains a vulnerability in `MediaDurationBlock` and `StepThroughItemsBlock` components. This vulnerability can lead to a denial of service due to unbounded disk space consumption. Defenders responsible for AutoGPT deployments should assess exposure and prioritize remediation to prevent potential operational impacts. The issue was patched in version 0.6.63, and defenders should verify affected versions and implement compensating controls.
- Vendor
- Significant-Gravitas
- Product
- AutoGPT
- CVSS
- HIGH 8.7
- 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. This vulnerability can lead to a denial of service, causing significant operational impact.
Why it matters
CVE-2025-32437 is a high-severity vulnerability in AutoGPT that can cause a denial of service due to unbounded disk space consumption. Defenders should assess exposure, prioritize remediation, and verify affected versions.
- Potential denial of service due to disk space exhaustion
- Need for verification of affected versions and remediation status
- Importance of monitoring disk space consumption and implementing compensating controls
Technical summary
A vulnerability in AutoGPT, a workflow automation platform, allows for a denial of service (DoS) due to unbounded consumption of disk space. The issue arises from the `MediaDurationBlock` and `StepThroughItemsBlock` components, which can lead to excessive disk space usage if not properly limited. The `MediaDurationBlock` downloads and stores videos in a temporary directory without deleting them before all nodes are done, and `StepThroughItemsBlock` can be used to iterate `MediaDurationBlock` multiple times without limiting the number of loops. Defenders should assess exposure, prioritize remediation, and verify affected versions to prevent potential operational impacts.
Defensive priority
High
Recommended defensive actions
- Upgrade AutoGPT to version 0.6.63 or later
- Limit the number of loops in `StepThroughItemsBlock`
- Monitor disk space consumption and implement cleanup mechanisms for temporary files
- Review compensating controls for exposed systems while remediation is scheduled and verified
- Check relevant monitoring, detection, and logs for exposed assets that need extra review
- Track exceptions, retest remediated assets, and close the item only after evidence is documented
- Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up
Evidence notes
The CVE record and NVD entry provide details on the vulnerability in AutoGPT, a workflow automation platform, which could lead to a denial of service (DoS) due to unbounded consumption of disk space. The issue was patched in version 0.6.63.
Sources and references
Verified primary and authoritative sources
-
CVE-2025-32437 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2025-32437
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2025-32437 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2025-32437
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-rg6v-m9x9-7wf9
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.