Quick answers
- Is CVE-2025-32422 exploited in the wild?
- No. Junglewise Threat Intelligence has no report of CVE-2025-32422 being exploited in the wild.
- How severe is CVE-2025-32422?
- 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-2025-32422?
- 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-2025-32422 attacked?
- It is attacked over the network, in a network appliance.
- Am I affected by CVE-2025-32422?
- 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 in the `StepThroughItemsBlock` and `FileStoreBlock` components. The `StepThroughItemsBlock` can iterate through an unlimited number of items in a list and pass them to `FileStoreBlock` for sequential downloading. While `FileStoreBlock` implements access time limits, it lacks restrictions on the total volume of data or the number of files stored in the working directory. An attacker can exploit this by providing a large list of external URLs (e.g., high-resolution videos), leading to disk space exhaustion. Furthermore, the use of countdown timers can delay agent cleanup, resulting in a persistent DoS state. This 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