AI Governance Institute
All governance templates →What AI agent security controls do we need as agent autonomy expands?

Implementation Kit

AI Agent Security Checklists and Permissions Register

The controls that decide whether an agent has earned more autonomy and whether you can stop it. Autonomy expansion criteria, a multi-agent trust hierarchy, a non-human identity register, scope-drift monitoring, and logged kill-switch propagation tests.

Who this is for: The security owner for agentic systems whose autonomy is growing.

Download the kit (Markdown) ↓5 artifacts. Every table also copies as CSV.

1. Autonomy expansion approval criteria

Spreadsheet

What must be true before an agent's scope grows, and who signs off at each tier.

Template

Autonomy tierMinimum operating historyMax error rate over that windowAdditional evidenceSign-off required
Tier 1: read + draftnone (launch)n/asign-off checklistBusiness + Risk
Tier 2: reversible writes<e.g. 60 days, 5,000 actions><e.g. < 1% blocked-gate rate, 0 Sev-1>monitoring clean; red-team clean+ Security
Tier 3: irreversible external actions with confirmation<e.g. 90 days at Tier 2><threshold>tabletop of a bad action; kill-switch test+ Legal + exec sponsor
Tier 4: irreversible external actions autonomouscase by case<threshold>dedicated security assessmentfull committee

Worked example

support-copilot request: Tier 1 to Tier 2 (allow KB article edits).

CriterionValueMeets threshold?
Operating history74 days, 11,200 actionsYes (>= 60 days / 5,000 actions)
Blocked-gate rate0.4%Yes (< 1%)
Sev-1 incidents0Yes
Sev-2 incidents1 (F-1, fixed)acceptable; 30 days clean since
Red-teamv1.6.1 clearedYes
Sign-offHead of Support, CRO, Head of Securitycomplete 2026-09-15

Outcome: approved; KB edits enabled behind human confirmation.

Acceptance criteria

  • Expansion criteria are defined before any agent asks for more autonomy.
  • Each tier has quantitative thresholds (history, error rate), not just a review.
  • Higher tiers require additional sign-off, and Tier 4 requires a dedicated security assessment.

2. Multi-agent trust hierarchy

Document

For systems where agents interact: whose instructions win, and what happens on conflict.

Template

One page plus a diagram. For any deployment with more than one agent.

  • Agents in the system: each with its role and autonomy tier
  • Instruction precedence: the order in which instruction sources are trusted (human operator > orchestrator > peer agent > tool output > retrieved content)
  • Delegation rules: which agent may instruct which, and what it may not delegate (an agent cannot grant another agent more authority than it holds)
  • Conflict resolution: what happens when two agents receive or issue conflicting directives (halt and escalate, defer to higher tier, operator decides)
  • Untrusted input rule: content from tools, retrieval, or external sources is never treated as an instruction
  • Logging: every cross-agent instruction is logged with both identities

Worked example

  • Agents: orchestrator (Tier 2), research sub-agent (Tier 1, read only), drafting sub-agent (Tier 1).
  • Precedence: human operator > orchestrator > sub-agent output > tool output > web content.
  • Delegation: the orchestrator may task sub-agents within its own scope; sub-agents cannot spawn further agents; no sub-agent can perform a write.
  • Conflict: if the research and drafting sub-agents return contradictory facts, the orchestrator halts the task and surfaces both to the operator rather than picking one.
  • Untrusted input: text fetched from the web is passed to sub-agents as data with an explicit "not instructions" wrapper.
  • Logging: orchestrator-to-sub-agent tasks logged with both service identities.

Acceptance criteria

  • Instruction precedence is written down and puts human and orchestrator above peer agents and any input content.
  • An agent cannot delegate authority it does not have.
  • Conflicts halt and escalate rather than resolving silently.

3. Non-human identity register

Spreadsheet

Every agent, sub-agent, and spawned process has its own identity with an expiry and a re-certification date.

Template

IdentityBelongs toParent identityScopesCreatedExpiresRe-certification dueOwner
<id><agent / sub-agent / job><parent or none><scopes>YYYY-MM-DDYYYY-MM-DDYYYY-MM-DD<name>

Worked example

IdentityBelongs toParentScopesCreatedExpiresRe-cert dueOwner
svc-orchestrator-prodorchestratornonetask queue; sub-agent spawn2026-06-012027-06-012026-12-01Platform
svc-research-prodresearch sub-agentsvc-orchestrator-prodweb fetch; kb:read2026-06-012027-06-012026-12-01Platform
tmp-run-8841spawned runsvc-orchestrator-prodinherits research scope; 1h TTL2026-09-052026-09-05n/aauto

Acceptance criteria

  • Every agent, sub-agent, and spawned process resolves to a distinct identity.
  • Each identity has an expiry and a re-certification date, treated like a service account.
  • Spawned short-lived identities inherit no more scope than their parent and carry a TTL.

4. Credential and permission scope-drift monitoring

Spreadsheet

Alert when an agent's effective permissions grow beyond its task definition, not only when it hits a hard limit.

Template

SignalDefinitionAlert thresholdResponse
New scope grantedAny permission added to an agent identityany changereview against task definition within 24h
Scope broader than task definitionEffective permissions exceed the documented task specany deltaopen a finding; revoke or update the spec
Unused broad scopeA granted scope not exercised in <N> days30 daysremove at next review
Cross-resource accessAgent accessed a resource outside its declared targetsanyblock and investigate
Spawned identity scopeA child identity requested more than the parent holdsanydeny; alert

Worked example

SignalThis periodThresholdAction
New scope grantedsvc-research-prod gained "kb:write"any changeReviewed: not in task spec (research is read-only). Revoked 2026-09-06; traced to a mis-scoped Terraform change.
Unused broad scopeorchestrator "admin:read" unused 45 days30 daysscheduled for removal
Cross-resource accessnoneany-

Acceptance criteria

  • Monitoring compares effective permissions to a documented task definition, not just a hard-coded ceiling.
  • Any scope increase triggers a review within a set time.
  • Findings are remediated by revoking scope or updating and re-approving the task definition.

5. Kill-switch propagation test log

Spreadsheet

Evidence that stopping the top-level agent actually stops every sub-agent and spawned process.

Template

Test dateScopeSub-agents / processes expectedReached by kill switchGaps foundFixRe-test date
YYYY-MM-DD<deployment><count / list><count><what did not stop>YYYY-MM-DD

Worked example

Test dateScopeExpectedReachedGapsFixRe-test
2026-08-30orchestrator + 2 sub-agents + spawned runs1 orchestrator, 2 sub-agents, up to 5 runsorchestrator + 2 sub-agents; 3 of 5 runs2 in-flight runs on a worker node finished their current tool call before stopping (up to 20s)add a hard interrupt check between tool calls2026-09-20
2026-09-20samesameall, within 3snone-2026-12-20

Acceptance criteria

  • The kill switch is tested against the real deployment topology, including spawned processes.
  • Every gap (something that did not stop, or stopped slowly) has a fix and a re-test.
  • The test is repeated on a cadence and after topology changes.

Governance controls this kit produces evidence for

Completing the artifacts above gives you a head start on the evidence requirements for these controls.

AGT-017
AGT-017

The expansion criteria table is the agentic autonomy expansion criteria and sign-off log.

AGT-004
AGT-004

The trust hierarchy document is the multi-agent trust hierarchy with conflict-resolution rules.

AGT-009
AGT-009

The kill-switch test log is the kill-switch propagation testing evidence.

AGT-011
AGT-011

The scope-drift monitoring is the agent permission and OAuth scope-drift detection.

AGT-022
AGT-022

The NHI register and test logs are the written attestation of which agentic governance controls are actually enforced.

This kit backs one playbook. Read the full guidance for the reasoning behind each artifact.

Decide what to implement next

Assess your governance gaps, then create an action plan with owners and target dates. Build and export without an account; sign in when you want to save your plan.

Start the AI governance assessment →