The OpenAI-Hugging Face hack was enabled by weak sandboxing. It is great that Nvidia is releasing open source tools for sandboxing AI agents. OpenWorker, our open-source agent harness supporting cybersecurity workflows, is proud to support this.
A sandbox gives an agent limited permissions. OpenWorker is building on Nvidia OpenShell and will support running each agent's commands inside a sandbox. Only the files relevant to the task go in. Secret API keys, your web browser login credentials, the ability to access arbitrary websites, are inaccessible to the agent by default. These restrictions are implemented in deterministic code rather than by prompting an LLM, which can make mistakes or be susceptible to prompt injections. Further, all actions are logged for monitoring and audit.
I'm grateful for @JensenHuang's leadership making AI agents more secure. OpenWorker (which @rohitcprasad and I are working on) will continue to improve security for agents.
1) “HISAO INTERNATIONAL (CAMBODIA) GARMENT CO., LTD.”
2) “AUROTIME NEW MATERIALS CO., LTD.”:
3) “SIHANOUKVILLE SPECIAL ECONOMY ZONE THERMAL POWER CO., LTD.”:
Thanks Council for the Development of Cambodia (CDC),who approved QIP ( Qualified Investment Project ) for our investors in SIHNAOUKVILLE SPECIAL ECONOMIC ZONE.
and Thanks all investors ,who are using our registration service.
Khmer / Chinese/ English Speaking Tel. 0962366028