← Solutions

Zero trust for AI agents

Default deny for non-human workloads, enforced outside the runtime.

Agents have no device posture and no human identity. Verify every connection, scope every destination, hold every unknown.

control.securd.com/gateway/acme/policies/prod-agents
Policy: prod-agents Published
Greywall Mode
Enforce
Hold Time
604800 s
Default Action
Deny Traffic
Allow list3 entries
  • bedrock-runtime.us-east-1.amazonaws.com
  • sts.us-east-1.amazonaws.com
  • api.internal.example
DoH providersMalwareC2ParkedSinkhole
A production agent policy: deny by default, three approved hosts, a seven day hold.
The problem

Zero trust was built for people and devices

Identity providers verify a person. Device posture verifies a laptop. An agent is a process with an API key that makes thousands of connections a minute to destinations a model chose. The controls that verify who and what do not answer where it may go.

No user to verify

The agent authenticates with a key. MFA and posture checks have nothing to evaluate.

Destinations decided at runtime

Least privilege on a static list does not cover a model that picks a new host per task.

Trust placed inside the runtime

An SDK or sidecar is part of the thing being attacked. The policy has to sit outside it.

How it works

Default deny by name, per role

Capabilities

Zero trust controls for agents

Default deny

A policy with Default Action Deny resolves its allow list and approved categories and nothing else.

Identity per instance

A DoH virtual site per agent instance. Events carry the instance name; approvals apply to the role.

Hold on first sight

The Greywall holds any name the policy has not resolved before, for as long as the policy says.

Every environment

Kubernetes, Docker, AWS, GCP, Azure, VMs, CI runners and workstations. The resolver exists in all of them.

Continuous verification

Every lookup is a decision with a reason, not a session that was trusted once.

Automation

Create and approve through the API with scoped keys. Every change recorded and revertible.

Limits

What stays in the firewall

Securd governs destinations reached by name. A connection to an IP address the agent already holds is governed by the egress firewall, which stays. Restrict port 53 and 853 to the Securd resolvers, block the DoH provider category in the policy, and a bypass attempt becomes a firewall log line.

control.securd.com/gateway/acme/logs
Traffic Logs site: research-agent
TimestampActionSiteQuery NameSource IPReason
2026-09-15 14:02:11acceptresearch-agentapi.openai.com10.40.2.17allow list
2026-09-15 14:02:11acceptresearch-agentapi.tavily.com10.40.2.17allow list
2026-09-15 14:02:14greywallresearch-agentcdn-assets-sync.top10.40.2.17first seen, held 24h
2026-09-15 14:02:14blockresearch-agentdns.google10.40.2.17category: DoH provider
2026-09-15 14:02:19threatresearch-agentupdate-check.pw10.40.2.17feed: c2-indicators
2026-09-15 14:02:31acceptfinance-agentapi.stripe.com10.40.3.8allow list
Accept, hold, block and threat in one minute of one agent.

Questions teams ask

Does Securd verify agent identity?

Securd identifies the requesting policy and site. Identity per instance is a virtual site address handled as a credential. It does not authenticate the model or the code.

Is this a service mesh replacement?

No. A mesh governs service-to-service traffic inside the cluster. Securd governs what the workload resolves on the way out, without a sidecar.

What about hardcoded IPs?

Out of scope for a resolver, in scope for the egress firewall. The deployment standard shows the two rules that close it.

Put one production agent on default deny

Learn for a week, enforce with a long hold, and watch the queue stay empty.