在 DAMO Academy 的 VideoLLaMA2(1.1 及更早版本)中发现了一个安全漏洞。该问题影响位于 videolla2/model/__init__.py 文件中的 load_pretrained_model 函数,属于模型加载组件。攻击者通过操纵 _name_or_path 参数,可绕过完整性校验值的正确验证。该漏洞可被远程利用,且利用方法已公开披露,存在被实际利用的风险。项目方已通过问题报告提前获知此漏洞,但截至目前尚未作出回应。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| DAMO Academy | VideoLLaMA2 | 1.0 |
cpe:2.3:a:damo_academy:videollama2:*:*:*:*:*:*:*:*
|
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC