Quick answers
- Is CVE-2025-32437 exploited in the wild?
- No. Junglewise Threat Intelligence has no report of CVE-2025-32437 being exploited in the wild.
- How severe is CVE-2025-32437?
- Informational severity, with a CVSS score of 8.7, published 18 June 2026.
- Which products and versions are affected?
- Significant-Gravitas AutoGPT < 0.6.63.
- Is there a fix for CVE-2025-32437?
- No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
- How is CVE-2025-32437 attacked?
- It is attacked over the network, in a network appliance.
- Am I affected by CVE-2025-32437?
- Check whether you run Significant-Gravitas AutoGPT at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.
Technical details
A Denial of Service (DoS) vulnerability exists in AutoGPT due to uncontrolled resource consumption (CWE-400) within the MediaDurationBlock and StepThroughItemsBlock components. The MediaDurationBlock downloads remote media files to a local temporary directory but fails to delete them immediately after processing or enforce disk space quotas. Because the StepThroughItemsBlock does not limit the number of iterations, an attacker can trigger repeated downloads of large files or numerous screenshots. This leads to disk space exhaustion on the host system. Furthermore, the use of long-running timers can delay the final cleanup of these temporary directories indefinitely. The issue is resolved in version 0.6.63.
Affected products
- Significant-Gravitas AutoGPT < 0.6.63
Timeline
- 2026-06-11: advisory: GitHub Security Advisory published
- 2026-06-18: disclosed: NVD publication date