CVE-2024-11449 | Server-Side Request Forgery in haotian-liu/llava

Exp

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.

Published: 2025-03-20 Last update: 2025-07-14 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2024-11449 is rated High Exploit Risk (66.1/100): CVSS High severity, with medium exploitation likelihood (EPSS 0.40%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2024-11449

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2024-11449

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-02 0.47% 0.40% -0.07%
2 2026-04-30 0.27% 0.47% +0.20%
3 2026-04-28 — 0.27% —

Full EPSS history (8 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2024-11449

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
7.5 3.0 HIGH
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:N)
Service keeps running; no real outage angle.
 3.9 3.6 [email protected]

Weakness enumeration for CVE-2024-11449

Affected software / configurations for CVE-2024-11449

Vendor Product Version Raw CPE
hliu large_language_and_vision_assistant 1.2.0 cpe:2.3:a:hliu:large_language_and_vision_assistant:1.2.0:*:*:*:*:*:*:*

References for CVE-2024-11449

cvelogic Threat Intelligence