What is the CVSS score of CVE-2025-62615?

CVE-2025-62615 has a CVSS 3.1 base score of 9.8 (Critical). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Which versions of AI / ML are affected by CVE-2025-62615?

A critical vulnerability (CVSS 9.8) in AutoGPT enables unauthenticated attackers to compromise AI agent platforms and automate malicious workflows at scale.

Is there a public PoC exploit available for CVE-2025-62615?

Yes, a public proof-of-concept exploit is available for CVE-2025-62615. Prioritise patching immediately. EPSS: 0.1%.

How to fix or mitigate CVE-2025-62615?

Within 24 hours: Identify all AutoGPT instances in your environment and isolate them from production networks; disable AutoGPT deployments if business continuity permits. Within 7 days: Conduct forensic audit of AutoGPT logs for suspicious agent creation, API calls, and data access; notify stakeholders of potential exposure. Within 30 days: Implement compensating controls (network segmentation, WAF rules, API throttling); maintain isolation until vendor releases patch; evaluate alternative orchestration platforms.

AI / ML CVE-2025-62615

CRITICAL

Server-Side Request Forgery (SSRF) (CWE-918)

2026-02-04 security-advisories@github.com

SSRF AI / ML Autogpt Platform

9.8

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

9.8 CRITICAL

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 12, 2026 - 21:54 vuln.today

PoC Detected

Feb 17, 2026 - 19:57 vuln.today

Public exploit code

CVE Published

Feb 04, 2026 - 23:15 nvd

CRITICAL 9.8

DescriptionGitHub Advisory

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.

AnalysisAI

AutoGPT has a Server-Side Request Forgery vulnerability (CVSS 9.8) allowing unauthenticated attackers to make the AI platform access internal network resources.

Technical ContextAI

AutoGPT has a CWE-918 SSRF vulnerability that allows unauthenticated attackers to make the platform send requests to arbitrary internal and external destinations.