M7 · HOW I RUN MY DAY · OP3

The Security Stack Playbook

No agent ever sees the whole vault. Bootstrap key, vertical vaults, machine identity, monthly audit.

6 SLIDES · ~8 MIN · PLAYBOOK OVERVIEW
Key Takeaways
  • No agent ever sees the whole vault.
  • 90% — of AI agents are over-permissioned — they hold rights they never use.
  • 3 of 10 — OWASP Agentic Top 10 risks tied directly to identity, secrets, and over-scoped access (LLM06, LLM07, LLM08).
  • 30 days — is the rotation cadence that catches drift before an auditor or attacker does. Calendar-locked, not best-effort.
  • Inventory every secret an agent currently has access to. Most CEOs find at least one that surprises them.
MODULE 7 · OPERATOR OP3

The Security Stack Playbook

No agent ever sees the whole vault.

BuildClub Academy
01 · THE THESIS

No agent ever sees
the whole vault.

The Thesis
02 · ARCHITECTURE

How the vault is actually shaped.

Takeaways
  • 1 One bootstrap key, stored offline. Used once at machine setup. Never seen by an agent.
  • 2 Vertical vaults — one per service domain. Gmail credentials live in one vault, AWS in another. No vault contains the union.
  • 3 Each agent gets a machine identity scoped to exactly the vault(s) it needs. Identity is the unit of audit.
  • 4 Monthly rotation runs as a scheduled job. The audit log is the only thing humans read.
03 · THE RULES

Five rules that keep the vault honest.

1
2
3
4
5
1
Bootstrap key stays offline
On a hardware key or a sealed envelope. Touched only at machine provisioning. Never on a laptop hard drive.
2
Vertical vaults, not horizontal
One vault per service domain (email, cloud, billing, code). Never one vault for everything.
3
Machine identity per agent
Each agent authenticates as itself, with scoped permissions. No shared service accounts. Identity is the audit unit.
4
Separate accounts for separate blast radii
Production data is not in the same cloud account as experiments. A blown experiment never reaches a customer record.
5
Monthly audit, calendar-locked
Last Friday of the month. Review identities, rotate keys, check the audit log. The discipline survives because the calendar enforces it.
04 · WHY

Why this matters: the breach you don't see coming.

90%
of AI agents are over-permissioned — they hold rights they never use.
OWASP Agentic Security Initiative
3 of 10
OWASP Agentic Top 10 risks tied directly to identity, secrets, and over-scoped access (LLM06, LLM07, LLM08).
OWASP LLM/Agentic Top 10
30 days
is the rotation cadence that catches drift before an auditor or attacker does. Calendar-locked, not best-effort.
Operator discipline
CLOSING

Four things to do Monday.

Monday Morning
  1. 1
    Inventory every secret an agent currently has access to. Most CEOs find at least one that surprises them.
  2. 2
    Pick a secret manager (Infisical, 1Password, Vault). Move every plaintext secret out of code and out of env files this month.
  3. 3
    Split your vaults vertically. Email creds in one. Cloud creds in another. Refuse to merge them.
  4. 4
    Calendar-lock the monthly rotation. Last Friday of the month. Treat it like board prep, not chore time.
OP3 · Questions CEOs Ask

Frequently Asked Questions

What is the core idea of The Security Stack Playbook?
No agent ever sees the whole vault.
What does the data say a CEO should pay attention to?
90% of AI agents are over-permissioned — they hold rights they never use. 3 of 10 OWASP Agentic Top 10 risks tied directly to identity, secrets, and over-scoped access (LLM06, LLM07, LLM08).
What should a CEO do Monday morning after reading The Security Stack Playbook?
Start here: Inventory every secret an agent currently has access to. Most CEOs find at least one that surprises them; Pick a secret manager (Infisical, 1Password, Vault). Move every plaintext secret out of code and out of env files this month; Split your vaults vertically. Email creds in one. Cloud creds in another. Refuse to merge them.
What are the steps in The Security Stack Playbook?
1) Bootstrap key stays offline; 2) Vertical vaults, not horizontal; 3) Machine identity per agent; 4) Separate accounts for separate blast radii; 5) Monthly audit, calendar-locked.
Where do the claims in The Security Stack Playbook come from?
The playbook cites Infisical machine identity model; OWASP Agentic Security Initiative; OWASP Agentic Security Initiative — over-permissioned agents; Infisical — machine identity for agents.
OP3 · Sources

All Sources in This Playbook

  • Infisical machine identity model
  • OWASP Agentic Security Initiative
  • OWASP Agentic Security Initiative — over-permissioned agents
  • Infisical — machine identity for agents
00 / 06