CVE-2025-0454
Published: 20 March 2025
Summary
CVE-2025-0454 is a high-severity SSRF (CWE-918) vulnerability in Agpt Autogpt Platform. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 27.8th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Other ATLAS/OWASP Terms risk domain.
Threat & Defense at a Glance
Threat & Defense Details
Likely Mitigating ControlsAI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Penetration testing attempts server-side requests to internal resources, identifying SSRF weaknesses for remediation.
Outbound connections to external resources can be monitored and limited at the boundary, reducing SSRF impact.
Validates server-side URLs and resource references to block SSRF attempts.
Detects server-side request forgery through monitoring of unexpected outbound connections.
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
SSRF vulnerability in autogpt enables exploitation of a public-facing application (T1190) by allowing attackers to bypass SSRF protections and make unauthorized requests to internal resources such as localhost services.
NVD Description
A Server-Side Request Forgery (SSRF) vulnerability was identified in the Requests utility of significant-gravitas/autogpt versions prior to v0.4.0. The vulnerability arises due to a hostname confusion between the `urlparse` function from the `urllib.parse` library and the `requests` library. A malicious…
more
user can exploit this by submitting a specially crafted URL, such as `http://localhost:\@google.com/../`, to bypass the SSRF check and perform an SSRF attack.
Deeper analysisAI
CVE-2025-0454 is a Server-Side Request Forgery (SSRF) vulnerability affecting the Requests utility in significant-gravitas/autogpt versions prior to v0.4.0. The issue stems from a hostname confusion between the `urlparse` function from the `urllib.parse` library and the `requests` library, allowing specially crafted URLs to bypass SSRF protections. Assigned CWE-918, it carries a CVSS v3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N), highlighting high integrity impact from network-accessible exploitation with low complexity and no privileges required.
A malicious user can exploit this vulnerability by submitting a crafted URL, such as `http://localhost:\@google.com/../`, to the affected Requests utility. This bypasses the SSRF check, enabling the attacker to forge requests from the server to unintended destinations, potentially leading to unauthorized access to internal services or resources. Exploitation requires only the ability to provide input URLs to the application, with no user interaction or privileges needed.
The vulnerability was addressed in autogpt v0.4.0 via commit ff065cd24c2289878c0abdb9adbf91c305f0d70a, as documented on GitHub. Additional details, including the bounty report, are available on Huntr at https://huntr.com/bounties/0664fdee-bdc2-4650-8075-74d7b8d3e308. Security practitioners should ensure upgrades to v0.4.0 or later to mitigate the issue.
This flaw occurs in AutoGPT, an open-source framework for autonomous AI agents, underscoring SSRF risks in AI/ML tooling that processes external URLs. No public evidence of real-world exploitation has been reported as of the CVE publication on 2025-03-20.
Details
- CWE(s)
Affected Products
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Other ATLAS/OWASP Terms
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- AutoGPT (significant-gravitas/autogpt) is an open-source AI agent framework that leverages LLMs like GPT for autonomous task execution, fitting 'AI Agent Protocols and Integrations'. The SSRF vulnerability in its Requests utility is reported via an AI/ML bug bounty platform.