PatchSiren cyber security CVE debrief
CVE-2025-32422 Significant-Gravitas CVE debrief
CVE-2025-32422 AutoGPT Denial of Service via Unrestricted File Downloads. The vulnerability in AutoGPT versions prior to 0.6.63 allows for a Denial of Service (DoS) attack through the `StepThroughItemsBlock` feature, which can be exploited to repeatedly download files from `FileStoreBlock` without access time limits or disk space consumption limits. This can lead to disk space exhaustion, causing a DoS. AutoGPT users and administrators should assess exposure and prioritize remediation to prevent potential DoS attacks.
- 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
AutoGPT users and administrators should assess exposure and prioritize remediation to prevent potential DoS attacks. This includes reviewing system configurations, restricting access to the `StepThroughItemsBlock` feature, and implementing compensating controls for exposed systems. Security teams should verify that appropriate measures are in place to mitigate the vulnerability and monitor for excessive disk space consumption.
Why it matters
CVE-2025-32422 is a high-severity vulnerability in AutoGPT that can be exploited for Denial of Service (DoS) attacks. AutoGPT users and administrators should assess exposure, prioritize remediation, and implement compensating controls to prevent potential disk space exhaustion.
- Potential Denial of Service (DoS) via disk space exhaustion
- Need to verify and restrict access to the `StepThroughItemsBlock` feature
- Requirement to upgrade to version 0.6.63 or later for patched functionality
Technical summary
The `StepThroughItemsBlock` feature in AutoGPT versions prior to 0.6.63 can be exploited to cause a Denial of Service (DoS) by repeatedly downloading files from `FileStoreBlock` without access time limits or disk space consumption limits. This vulnerability allows for disk space exhaustion, leading to a DoS attack. The issue is patched in version 0.6.63, which limits the exploitation of this feature. Affected AutoGPT users and administrators should assess exposure and prioritize remediation to prevent potential DoS attacks.
Defensive priority
High
Recommended defensive actions
- Upgrade AutoGPT to version 0.6.63 or later
- Implement monitoring for excessive disk space consumption
- Restrict access to the `StepThroughItemsBlock` feature
- 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 describe a Denial of Service (DoS) vulnerability in AutoGPT versions prior to 0.6.63. The vulnerability is caused by the `StepThroughItemsBlock` feature, which can be used to repeatedly download files from `FileStoreBlock` without access time limits or disk space consumption limits. Evidence is based on CVE and NVD descriptions, with limitations on source-provided details.
Sources and references
Verified primary and authoritative sources
-
CVE-2025-32422 CVE Program record
Publisher, destination, and source semantics verified
URL: https://www.cve.org/CVERecord?id=CVE-2025-32422
CVE Program - Official CVE Program record with source-provided CVE metadata.
-
CVE-2025-32422 NVD vulnerability detail
Publisher, destination, and source semantics verified
URL: https://nvd.nist.gov/vuln/detail/CVE-2025-32422
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-9fr4-9jj9-mhh6
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.