Critical severity · published Feb 4, 2026
CVE-2025-62615
AutoGPT has SSRF vulnerability in ReadRSSFeedBlock
9.8
CVSS
0.4%
EPSS
No
On KEV
Description
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.34, in RSSFeedBlock, the third-party library urllib.request.urlopen is used directly to access the URL, but the input URL is not filtered, which will cause SSRF vulnerability. This issue has been patched in autogpt-platform-beta-v0.6.34.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.4% · higher than 36% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
AU
AutoGPT · Significant-Gravitas
< autogpt-platform-beta-v0.6.34 · source: vendor
AP
Autogpt Platform · Agpt
before 0.6.34 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-62615
CVE.org
https://www.cve.org/CVERecord?id=CVE-2025-62615
Exploit
https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-r55v-q5pc-j57f
More from AutoGPT
9.8
CVE-2025-62616
AutoGPT has SSRF vulnerability in SendDiscordFileBlock
8.8
CVE-2026-55237
AutoGPT SignUp Page has DOM-Based XSS and Open Redirect
8.8
CVE-2026-26020
AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)
8.8
CVE-2026-24780
AutoGPT is Vulnerable to RCE via Disabled Block Execution
8.7
CVE-2025-32437
AutoGPT has a DoS vulnerability in MediaDurationBlock