DAMO Academy VideoLLaMA2 Model Loading __init__.py load_pretrained_model integrity check
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
Summary
The DAMO Academy VideoLLaMA2 video-language AI model software is affected, specifically its code for loading pretrained models. An attacker could remotely supply a manipulated model path that bypasses the software's integrity check, which could allow untrusted or tampered model content to be loaded.
Summarized by anthropic/claude-haiku-5.5. Verify details against the original sources.
Read the original 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.
Timeline
- CVE published
- First seen by cve.now
Affected versions
- DAMO Academy VideoLLaMA2
1.0, 1.1