CVE intelligence and bounded remediation
CVE-2024-11449 — Hliu Large Language And Vision Assistant security vulnerability
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.
- Severity
- High
- CVSS
- 7.5 (3.0)
- Published
- 2025-03-20
- CISA KEV
- Not currently listed
- Ecosystem
- software/application
- Weaknesses
- CWE-918
Affected products
- hliu / large_language_and_vision_assistant / 1.2.0
Matched remediation archetype
Server-side request forgery and unintended proxying
This catalog composition supplies bounded fallback guidance. Explicitly reviewed curated workflows load with the complete record below.
Check exposure
- Inventory server-side URL fetchers, webhooks, importers, previews, redirects, proxies, and protocol handlers reachable from untrusted input.
- Map egress paths to internal services, metadata endpoints, loopback, private address space, and privileged control planes.
- Review DNS resolution, redirect, proxy, credential-forwarding, and URL parsing behavior without requesting sensitive targets.
Remediate safely
- Replace arbitrary destinations with named integrations or a strict allowlist of schemes, hosts, ports, and paths.
- Resolve and validate every destination and redirect hop, then enforce egress policy independently of application checks.
- Remove ambient credentials and sensitive headers from fetchers; apply response size, time, and content limits.
Authoritative sources
Complete CVE record and remediation plan
The detailed catalog view below loads this exact record, its source evidence, and the full seven-phase agentic change plan.