Log in Start free

Vulnerability · Published Oct 27, 2026 · Assigned by VulDB

CVE-2026-116608DAMO Academy VideoLLaMA2 Model Loading __init__.py load_pretrained_model integrity check

Medium 5.4

In plain English

A medium-severity insufficient verification of data authenticity in VideoLLaMA2 from DAMO Academy. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.1% (higher than 4% of all known vulnerabilities).

Severity (CVSS 3.1)5.4Medium
Exploit odds (30 days)0.1%top 95.8% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

A security vulnerability has been detected in DAMO Academy VideoLLaMA2 up to 1.1. Affected by this issue is the function load_pretrained_model of the file videollama2/model/__init__.py of the component Model Loading. The manipulation of the argument _name_or_path leads to improper validation of integrity check value. Remote exploitation of the attack is possible. The exploit has been disclosed publicly and may be used. The project was informed of the problem early through an issue report but has not responded yet.

Affected products (as reported)

VendorProductVersions
DAMO Academy VideoLLaMA2 1.01.1

Weakness: CWE-354, CWE-345 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:L/E:P/RL:X/RC:C

References