Information disclosure in Significant-gravitas Autogpt
CVE-2025-31491
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.1, AutoGPT allows of leakage of cross-domain cookies and protected headers in req…
Vulnerability class: Information Disclosure
EPSS: 0.003 (53.0th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 8.6 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N.
Affected products
- Significant-gravitas Autogpt — versions < 0.6.1
Weakness classification (CWE)
References
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-ggcm-93qg-gfhp (x_refsource_CONFIRM)
Frequently asked questions
- What is CVE-2025-31491?
- CVE-2025-31491 is a high-severity vulnerability in Significant-gravitas Autogpt, classified under Information Disclosure. CVSS score: 8.6/10. Published 2025-04-14.
- How severe is CVE-2025-31491?
- High severity. CVSS v3 base score is 8.6 out of 10.