CVE-2025-62615: AutoGPT has SSRF vulnerability in ReadRSSFeedBlock
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.
Affected Software
Event History
Frequently Asked Questions
What is the severity of CVE-2025-62615?
CVE-2025-62615 has been classified as a medium severity vulnerability due to its potential impact on system security.
How do I fix CVE-2025-62615?
To mitigate CVE-2025-62615, update to the latest version of AutoGPT, specifically autogpt-platform-beta-v0.6.34 or later.
What type of vulnerability is CVE-2025-62615?
CVE-2025-62615 is a Server-Side Request Forgery (SSRF) vulnerability found in the ReadRSSFeedBlock component.
Which versions of AutoGPT are affected by CVE-2025-62615?
AutoGPT versions prior to autogpt-platform-beta-v0.6.34 are affected by CVE-2025-62615.
What are the potential impacts of CVE-2025-62615?
CVE-2025-62615 can allow attackers to make unauthorized requests from the server, potentially leading to data exposure.