What is the CVSS score of CVE-2024-11449?

CVE-2024-11449 has a CVSS 3.0 base score of 7.5 (High). CVSS vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N. EPSS exploitation probability: 0.1%.

Which versions of Large Language And Vision Assistant are affected by CVE-2024-11449?

Organizations using haotian-liu/llava face notable risk from CVE-2024-11449, a server-side request forgery vulnerability rated CVSS 7.5.

Is there a public PoC exploit available for CVE-2024-11449?

Yes, a public proof-of-concept exploit is available for CVE-2024-11449. Prioritise patching immediately. EPSS: 0.1%.

How to fix or mitigate CVE-2024-11449?

Within 7 days: Identify all affected systems running haotian-liu/llava and apply vendor patches promptly. Implement egress filtering and URL validation for server-side requests.

Large Language And Vision Assistant CVE-2024-11449

HIGH

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

2025-03-20 security@huntr.dev

Information Disclosure SSRF Authentication Bypass Large Language And Vision Assistant

7.5

CVSS 3.0 · NVD

Severity by source

NVD PRIMARY

7.5 HIGH

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

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

None

Availability

None

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 18:32 vuln.today

PoC Detected

Jul 14, 2025 - 17:36 vuln.today

Public exploit code

CVE Published

Mar 20, 2025 - 10:15 nvd

HIGH 7.5

DescriptionCVE.org

A vulnerability in haotian-liu/llava version 1.2.0 (LLaVA-1.6) allows for Server-Side Request Forgery (SSRF) through the /run/predict endpoint. An attacker can gain unauthorized access to internal networks or the AWS metadata endpoint by sending crafted requests that exploit insufficient validation of the path parameter. This flaw can lead to unauthorized network access, sensitive data exposure, and further exploitation within the network.

AnalysisAI

A vulnerability in haotian-liu/llava version 1.2.0 (LLaVA-1.6) allows for Server-Side Request Forgery (SSRF) through the /run/predict endpoint. Rated high severity (CVSS 7.5), this vulnerability is remotely exploitable, no authentication required, low attack complexity. Public exploit code available and no vendor patch available.

Technical ContextAI

This vulnerability is classified as Server-Side Request Forgery (SSRF) (CWE-918), which allows attackers to make the server perform requests to unintended internal or external resources. A vulnerability in haotian-liu/llava version 1.2.0 (LLaVA-1.6) allows for Server-Side Request Forgery (SSRF) through the /run/predict endpoint. An attacker can gain unauthorized access to internal networks or the AWS metadata endpoint by sending crafted requests that exploit insufficient validation of the path parameter. This flaw can lead to unauthorized network access, sensitive data exposure, and further exploitation within the network. Affected products include: Hliu Large Language And Vision Assistant. Version information: version 1.2.0.

RemediationAI

No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Validate and allowlist destination URLs, block requests to internal networks, use network segmentation.

CVE-2024-11449 vulnerability details – vuln.today

Back

Large Language And Vision Assistant CVE-2024-11449

Severity by source

CVSS VectorNVD

Lifecycle Timeline

DescriptionCVE.org

AnalysisAI

Technical ContextAI

RemediationAI

Share

External POC / Exploit Code