Security readout for executives and security teams
Plain-English summary
AutoGPT versions before 0.6.63 can let an unauthenticated network attacker trigger excessive video processing in LoopVideoBlock. Because loop counts are not limited, the system can create very large files and fill disk space, causing denial of service. Organizations running exposed AutoGPT workflows should treat this as urgent availability risk.
Executive priority
Prioritize remediation for any exposed or shared AutoGPT deployment because this flaw can directly disrupt service availability. Upgrade is the clearest remediation named by the source. This is not described as data theft or code execution, but disk exhaustion can still create operational outages.
Technical view
CVE-2025-32392 is a CWE-400 uncontrolled resource consumption issue in Significant-Gravitas AutoGPT before 0.6.63. LoopVideoBlock accepts user-controlled video looping or extension parameters without resource limits. Excessive looping can produce oversized output written to disk, exhausting storage. CVSS v4.0 score is 8.7 with network attack vector, low complexity, no privileges, and no user interaction.
Likely exposure
Exposure is most relevant where AutoGPT instances or workflows using LoopVideoBlock accept untrusted or internet-accessible input. The source identifies affected versions as AutoGPT before 0.6.63. If AutoGPT is internal-only and input is tightly controlled, practical exposure is lower but still depends on tenant and workflow trust boundaries.
Exploitation context
The advisory describes a denial-of-service condition from attacker-controlled loop counts causing disk exhaustion. The provided sources do not state active exploitation, public exploit availability, or CISA KEV listing. The attack does not require privileges or user interaction according to the CVSS vector.
Researcher notes
Evidence is limited to the CVE record and GitHub security advisory. The root issue is missing resource controls in LoopVideoBlock output generation. No exploit code, exploitation-in-the-wild claim, or additional affected products are provided in the supplied sources.
Mitigation direction
- Upgrade AutoGPT to version 0.6.63 or later.
- Restrict access to AutoGPT workflows accepting video input.
- Limit untrusted use of LoopVideoBlock until upgraded.
- Apply disk quotas and monitoring where feasible.
- Review vendor advisory for any updated guidance.
Validation and detection
- Inventory AutoGPT deployments and record installed versions.
- Confirm any version before 0.6.63 is prioritized for remediation.
- Identify workflows using LoopVideoBlock or video-processing input.
- Check whether those workflows accept unauthenticated or untrusted input.
- Review disk usage alerts for AutoGPT hosts.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-400: Exact CWE lookup
Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupCVE-2025-32392 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- High
- CVSS
- 8.7 (4.0)
- Known Exploited
- No
- Published
Vector: 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
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
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——GitHub_MVulnerability scoring details
Base CVSS 4.0 score
8.7HighVector: 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
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-267x-8jx3-gg6wCVE reference, GitHub_M · x_refsource_CONFIRM
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Uncontrolled Resource Consumption
Uncontrolled Resource Consumption represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.