Security

Zero Trust for agent identity and execution.

Verify explicitly, apply least privilege and assume breach across identity, model, tool, workload, data and evidence boundaries.

Control design

Enforcement reaches the actual point of action.

Enforcement pointControl functionFailure posture
API gateway / brokerValidate passport, scope, target, obligations and revocation.Fail closed for protected or high-impact actions.
Agent tool interceptorEvaluate individual tool calls and route approvals.Block unknown tools; cache only short-lived low-risk decisions.
Kubernetes admission / sidecarValidate workload identity, image, region and runtime limits.Reject non-compliant workloads; quarantine drift.
Model gatewayRestrict provider, version, prompt handling and data class.Block unapproved model substitution.
Business adapterEnforce transaction, case, procurement or record-level conditions.Hold and open review on critical exceptions.
Threat model

Design against identity, delegation, runtime and evidence attacks.

Agent impersonationCPID verification, proof-of-possession, short-lived credentials and issuer/status checks.
Token replayNonce/audience binding, expiry, replay detection, workload binding and mTLS where appropriate.
Delegation launderingVisible delegation graph, authority ceiling, sponsor and no self-escalation.
Model substitutionModel Passport, endpoint/version allowlist and approval gates.
Workload driftImage digest, admission control, attestation and material-change triggers.
Evidence tamperingSigned events, append-only storage, hashes, controlled retention and immutable audit patterns.
Fail-safe rule

When identity, signature, status, policy, workload context or safe operating conditions cannot be verified, restrict, defer, isolate or escalate rather than continue autonomously.