在 InternScience InternAgent 1.5.0 中发现一个安全弱点。该问题影响组件 LoRA Loading 中文件 tasks/AutoChem/code/experiment.py 的 train 函数。攻击者可通过操纵参数 base_model_name_or_path,导致系统引入来自不可信控制域的功能。此攻击可远程发起,且利用代码已公开,可能被用于实施攻击。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 |
|---|---|---|---|---|
| InternScience | InternAgent | 1.5.0 |
cpe:2.3:a:internscience:internagent:*:*:*:*:*:*:*:*
|
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POCNo comments yet