Originally published at: Sandboxing Agentic AI Workflows with WebAssembly | NVIDIA Technical Blog
Agentic AI workflows often involve the execution of large language model (LLM)-generated code to perform tasks like creating data visualizations. However, this code should be sanitized and executed in a safe environment to mitigate risks from prompt injection and errors in the returned code. Sanitizing Python with regular expressions and restricted runtimes is insufficient, and…
1 Like