AG-006: No Human Approval for Destructive Actions

What this rule means

Agent can execute/write/delete without any human confirmation step.

Why it matters

Replit agent wiped a production database (July 2025) with no approval gate.

How to fix it

Add interrupt_before (LangGraph) or HumanApprovalCallbackHandler (LangChain).

Detect it

pip install lucin
lucin scan .                  # all rules
lucin explain AG-006          # this rule, in your terminal

Findings carry a file:line and, where the rule supports it, a witness path showing the flow that triggered it. Precision and recall for the whole rule set, with the commands that regenerate them, are on the benchmarks page — and the gaps are on limits.

← All detection rules