If you've built autonomous agents with CrewAI, LangGraph, or Microsoft AutoGen, you know that giving an LLM access to bash tools or database queries is genuinely terrifying.
A single jailbreak, prompt injection, or weird hallucination can run:
bash
rm -rf /
DROP TABLE production_users;
().__class__.__base__.__subclasses__() # Sandbox breakout
Top comments (1)
The local policy layer is sensible, but sub-50µs only describes decision latency. The harder problem is keeping AST or policy evaluation aligned with runtime context and preventing encoded or indirect commands from bypassing static checks. Do you fail closed when the parser cannot classify an action?