Kiro

Coding agent (IDE) · AWS · Last checked 2026-10-16

permissions.yaml rules with allow, ask and deny, where deny always wins. Supervised mode prompts before actions.

Overall: B (2.00 avg over 3 verified criteria)

Lock this down first

Use Supervised mode and avoid wildcard trusted commands.

Scorecard

Criterion	Rating	Notes
Permission granularity	3/3
Human approval gates	2/3
Sandboxing	Unverified	Not confirmed in the docs we checked.
Secrets handling	Unverified	Not confirmed in the docs we checked.
Audit logs	1/3	No built-in audit log found. PostToolUse hooks can write your own JSONL trail.
Kill switch / interrupt	Unverified	Not confirmed in the docs we checked.
Network egress control	Unverified	Not confirmed in the docs we checked.

Unverified: Sandboxing, Secrets handling, Kill switch / interrupt, Network egress control. That means we could not confirm it in public docs, not that it is missing.

Sources

https://kiro.dev/docs/permissions/
https://kiro.dev/docs/privacy-and-security/
https://kiro.dev/docs/hooks/types/