What is the CVSS score of CVE-2025-62616?

CVE-2025-62616 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-2025-62616?

CVE-2025-62616 is a critical vulnerability affecting AutoGPT deployments with a 9.8 CVSS score and active public exploits, creating immediate risk of unauthorized access or system compromise for…

Is there a public PoC exploit available for CVE-2025-62616?

Yes, a public proof-of-concept exploit is available for CVE-2025-62616. Prioritise patching immediately. EPSS: 0.1%.

How to fix or mitigate CVE-2025-62616?

Within 24 hours: Conduct an immediate inventory of all AutoGPT deployments and identify which systems are internet-facing or process sensitive data; implement emergency access controls and increase monitoring for suspicious activity. Within 7 days: Deploy network segmentation to isolate AutoGPT instances, restrict API access to trusted sources only, and disable non-essential AutoGPT features; establish incident response procedures specific to potential AutoGPT compromise. Within 30 days: Evaluate migration to alternative workflow automation platforms if AutoGPT is business-critical; maintain continuous monitoring and prepare for rapid patch deployment when available.

AI / ML CVE-2025-62616

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 - 20:05 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 SendDiscordFileBlock, the third-party library aiohttp.ClientSession().get 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.