Security readout for executives and security teams
Plain-English summary
AutoGPT versions before 0.6.63 can let a low-privileged user exhaust server disk space through media workflow behavior. The result is denial of service: agents or the host may stop working because temporary video and audio files are not adequately cleaned up or bounded.
Executive priority
Treat this as a near-term availability risk for any shared or production AutoGPT deployment. Prioritize upgrade during the next maintenance window, sooner for internet-facing or multi-user agent platforms.
Technical view
The issue affects Significant-Gravitas AutoGPT before 0.6.63. AddAudioToVideoBlock stores downloaded video and audio in a temporary directory and does not adequately delete or limit disk usage. StepThroughItemsBlock can iterate related media processing without loop limits, enabling resource exhaustion. CVSS 4.0 score is 7.1.
Likely exposure
Exposure is likely where AutoGPT before 0.6.63 is deployed and users can create or run workflows using the affected media and iteration blocks. Shared automation platforms, hosted agent environments, and disk-constrained workers have higher operational risk.
Exploitation context
The provided sources do not cite active exploitation, and the CVE is not marked KEV. Exploitation requires low privileges and no user interaction, with impact focused on availability through disk exhaustion rather than data theft or code execution.
Researcher notes
The root weakness maps to CWE-400: uncontrolled resource consumption. Evidence supports disk-space exhaustion through unbounded looping and incomplete temporary file cleanup. The source bundle names version 0.6.63 as patched but does not provide further exploit telemetry.
Mitigation direction
- Upgrade AutoGPT to version 0.6.63 or later.
- Review the GitHub advisory for vendor-confirmed remediation details.
- Restrict untrusted workflow execution until upgraded.
- Monitor worker disk usage and temporary media directories.
- Apply operational disk quotas where supported by your deployment platform.
Validation and detection
- Inventory AutoGPT deployments and confirm versions are at least 0.6.63.
- Identify workflows using AddAudioToVideoBlock, StepThroughItemsBlock, or MediaDurationBlock.
- Check recent logs for abnormal media workflow repetition or disk growth.
- Confirm temporary media files are cleaned after benign workflow completion.
- Verify monitoring alerts cover low disk space on AutoGPT workers.
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-2025-32436 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
- 7.1 (4.0)
- Known Exploited
- No
- Published
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:L
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:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:L——GitHub_MVulnerability scoring details
Base CVSS 4.0 score
7.1HighVector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:L
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-g26x-xwc5-7p44CVE 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.