Large Language And Vision Assistant vulnerabilities
2 known vulnerabilities in Large Language And Vision Assistant from Hliu. 2 are rated high or critical. Each entry lists the affected versions and the release that fixes it, where the vendor has published one.
2vulnerabilities
0critical
2high
0exploited
7.5average CVSS score
Latest first
- 7.5 High severity
haotian-liu/llava: Uncontrolled Resource Consumption
A Denial of Service (DoS) vulnerability exists in the file upload feature of haotian-liu/llava, specifically in Release v1.2.0 (LLaVA-1.6). The vulnerability is due to improper handling of form-data with a large filename in the file upload request. By sending
- 7.5 High severity
haotian-liu/llava: Server-Side Request Forgery
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 reques