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%.

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 Agpt

9.8

CVSS 3.1 · GitHub Advisory

View

Vulnerability Assessment

Weakness	CWE CWE-918 OWASP Top 10:2025 A01:2025 - Broken Access Control ASVS 5.0 V4 - API and Web Service URL allowlisting, SSRF prevention MITRE ATT&CK 2 techniques across 2 tactics: Initial Access, Credential Access The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up. Sign in to read
Impact	CVSS 9.8 with PoC. Two SSRF vectors indicate systemic lack of URL validation in AutoGPT.
Exploit ScenarioDerived	An attacker uses this alternative SSRF endpoint when the first is mitigated.

Act Now Prioritize within 24-48h. Why: CRITICAL severity + public POC available.

No patch listed yet 0.1% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Mar 12, 2026

AutoGPT has a second SSRF vulnerability (CVSS 9.8) in a different endpoint, providing an additional path to access internal network resources.

Earlier versions of this analysis (1)

v1 Mar 12, 2026 - 21:54 CVSS 9.8

Second SSRF in AutoGPT provides additional internal network access vector.

RemediationAI

Update AutoGPT. Address both SSRF vulnerabilities.

Affects your stack

Find out whether the stacks and servers you run are on an affected version.

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Technical ContextAI · show details

A second CWE-918 SSRF in AutoGPT, distinct from CVE-2025-62615 but with the same impact.

Know when AI / ML gets its next vulnerability

Watch products and get an email when something new is published
Check this CVE against your own stack and servers
Exploit and PoC references, threat intelligence from 22 sources

Continue with Google Continue with GitHub

No credit card · 7-day full trial

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

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

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.

Executive ViewAI

Why It Matters

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 organizations using this platform. With no patch currently available, any organization deploying AutoGPT agents in production environments faces potential data breach, workflow disruption, and loss of control over automated processes. This requires urgent assessment and mitigation to prevent exploitation.

Business Impact: Severe

Compensating Controls

Implement WAF rules to restrict AutoGPT API endpoints to known trusted sources only; segment AutoGPT infrastructure from production networks using network firewalls; disable AutoGPT agent auto-execution and require manual approval for workflow triggers; enforce strict authentication and API key rotation; enable comprehensive audit logging of all AutoGPT activities; implement rate limiting on API requests; consider temporary suspension of non-critical AutoGPT deployments until patch availability.

Threat Intelligence Overview

EPSS Score

0.1%

Top 82% exploitable

Exploit

POC

Public exploit code exists

Data Quality

4 sources

Confidence: Medium

NVD

CVE.org

EPSS

GitHub

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue

Severity CRITICAL

CISA KEV No

Public POC Yes

EPSS 0.1%

Patch available No

Active threat No

Deciding rule

CRITICAL severity + public POC available

What every action level means

Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.

Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.

This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.

This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.

Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision· derived

Out-of-Cycle

Exploitation· derived

Poc

System Exposure· derived

Open

Automatable· derived

Yes

Human Impact

Very High

Priority Score

Low Medium High Critical

KEV: 0

EPSS: 0

CVSS: +49

PoC: +20

Weaponized: 0

Threat intel: 0

Gov advisory: 0

Attack Technique

Server-Side Request Forgery HIGH

Server-Side Request Forgery exploits applications that fetch remote resources based on user-supplied URLs.

Affected Products (CPE)GitHub Advisory

cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:*

More in AI / ML

View all

CVE-2026-23744 CRITICAL Act Now POC

9.8 Jan 16

MCPJam Inspector versions 1.4.2 and earlier allow unauthenticated remote code execution through missing authentication i

CVE-2026-0768 CRITICAL Emergency POC

9.8 Jan 23

Langflow has a code injection vulnerability in the code component (EPSS 2.6%) enabling remote code execution through the

CVE-2026-0769 CRITICAL Emergency POC

9.8 Jan 23

Langflow has an eval injection in eval_custom_component_code (EPSS 2.0%) enabling remote code execution through crafted

CVE-2024-8859 HIGH Act Now POC

7.5 Mar 20

A path traversal vulnerability exists in mlflow/mlflow version 2.15.1. Rated high severity (CVSS 7.5), this vulnerabilit

CVE-2026-27966 CRITICAL Act Now POC

9.8 Feb 26

Code injection in Langflow CSV Agent node before 1.8.0. The node hardcodes allow_dangerous_code=True, enabling arbitrary

CVE-2026-27597 CRITICAL Act Now POC

10.0 Feb 25

Sandbox escape in Enclave JavaScript sandbox before 2.11.1. Enclave is designed for safe AI agent code execution — the e

CVE-2026-22686 CRITICAL Act Now POC

10.0 Jan 14

enclave-vm JavaScript sandbox (before 2.7.0) has a critical sandbox escape. When a tool invocation fails, a host-side Er

CVE-2025-2828 CRITICAL Act Now POC

10.0 Jun 23

A remote code execution vulnerability in langchain-ai/langchain (CVSS 10.0). Risk factors: public PoC available. Vendor

CVE-2026-1470 CRITICAL Act Now POC

9.9 Jan 27

n8n has a fifth critical RCE vulnerability (CVSS 9.9) in the Expression evaluator, enabling code execution through craft

CVE-2026-24770 CRITICAL Act Now POC

9.8 Jan 27

Path traversal vulnerability in RAGFlow RAG engine version 0.23.1 allows unauthenticated attackers to read arbitrary fil

CVE-2026-22688 CRITICAL Act Now POC

9.9 Jan 10

WeKnora LLM framework (before 0.2.5) allows authenticated users to inject MCP stdio commands that the server executes as

CVE-2026-30861 CRITICAL Act Now POC

9.9 Mar 07

OS command injection in WeKnora from version 0.2.5 allows authenticated users to execute arbitrary system commands. CVSS

Same weakness CWE-918 – Server-Side Request Forgery (SSRF)

View all

CVE-2021-34473 CRITICAL POC

9.1

CVE-2021-26855 CRITICAL POC

9.1

CVE-2021-21985 CRITICAL POC

9.8

CVE-2022-41040 HIGH POC

8.8

CVE-2024-21893 HIGH POC

8.2

CVE-2021-40438 CRITICAL POC

9.0

CVE-2021-22054 HIGH POC

7.5

CVE-2021-21975 HIGH POC

7.5

Same technique SSRF

View all

CVE-2016-3718 MEDIUM POC

5.5

Search Externally

GitHub PoC

Exploit-DB PacketStorm Snyk Rapid7 Nuclei Templates Trickest PoC

Back