Directory / OpenAI Agents SDK
OpenAI Agents SDK
needs_approval on tools pauses a run and returns interruptions you approve or reject. Input, output and tool guardrails run checks, and built-in tracing records tool calls and handoffs.
Lock this down first
Mark every write tool needs_approval=True and keep sensitive-data tracing off in production.
Scorecard
| Criterion | Rating | Notes |
|---|---|---|
| Permission granularity | 2/3 | |
| Human approval gates | 3/3 | |
| Sandboxing | Unverified | Not confirmed in the docs we checked. |
| Secrets handling | Unverified | Not confirmed in the docs we checked. |
| Audit logs | 3/3 | Tracing covers model calls, tool calls, handoffs and guardrails. |
| Kill switch / interrupt | 2/3 | Guardrail tripwires halt a run. |
| Network egress control | Unverified | Not confirmed in the docs we checked. |