CVE-2025-62615CRITICAL 9.8EPSS p27.4%

CVE-2025-62615CVE-2025-62615

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.

Scoring

CVSS 3.19.8 (CRITICAL)
VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS0.36% probability of exploitation · percentile 27.4% · 2026-06-18T12:00:27Z
Published2026-02-04
Last modified2026-02-17

Underlying weaknesses· 1

CWE-918

References

  1. https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-r55v-q5pc-j57f

1

TypeTargetConfidenceTier
WeaknessServer-Side Request Forgery (SSRF)cwe-9180%live

Related by meaning· 6

Nearest entities by semantic similarity across the cs-graph corpus.

CVE
CVE-2025-62616
CVE
CVE-2025-22603
CVE
CVE-2025-1040
CVE
CVE-2025-31491
CVE
CVE-2026-26020
CVE
CVE-2025-28197
Sourced from NVD + FIRST.org EPSS. Curated for EU compliance use cases by Adam Lundqvist, Founder at SQUR.