HazelJS LogoHazelJS
HazelJS Blog

How to Secure AI Agent Tool Calls

Author
HazelJS Team
10/21/2026
General
How to Secure AI Agent Tool Calls
← Back to Blog

Least privilege, Gatekeeper allow/deny/require-approval, hazeld secrets, and audit timelines — without unsupported security claims.

Securing tool calls means deciding who may run which tool with which credentials, and recording what happened. HazelJS focuses on fail-closed authorization — not marketing claims of “prompt injection proof.”

Agents are powerful because tools mutate the world. Security for agents is therefore mostly tool-path security, not “a smarter system prompt.”

Threat model (practical)

Assume the model can be steered. Design so that:

  1. Dangerous capabilities are not registered unless needed (Skillgate).
  2. Registered tools still need authorization per call (Gatekeeper).
  3. High-impact tools need a human (require-approval + durable HITL).
  4. Credentials live in a node-scoped secret store, not in prompts.
  5. Every decision leaves an audit trail (timelines / hazel logs).

This page does not claim prompt-injection immunity, a hosted compliance product, or OS-level sandboxing. Agents share your Node process by default — design isolation accordingly.

Practical controls

1. Curate capabilities with Skillgate

Do not dump every OpenAPI path into the agent. Skillgate classifies skills (read / write / approval) so the model only sees a governed set.

2. Authorize with Gatekeeper

import { AgentGatekeeper, fromFunction } from '@hazeljs/​agent-gatekeeper';

const gatekeeper = new AgentGatekeeper({
  policies: [
    fromFunction('refunds.create', async (ctx) =>
      ctx.amount > 50 ? 'require-approval' : 'allow',
    ),
  ],
});

Outcomes are allow, deny, or require-approval. Confidence from Decision Runtime informs policy — it never grants permission by itself.

3. Approve sensitive ops via durable HITL

hazel approvals
hazel approve <id>
hazel deny <id>

Approvals must survive process restart when durable suspend is enabled. Chat DMs are not a control plane.

4. Store secrets on hazeld

hazel secret set OPENAI_API_KEY
hazel secret has OPENAI_API_KEY

Secrets target hazeld’s encrypted file store — local-first, not a cloud vault by default.

5. Audit with run timelines

Use hazel logs / inspector timelines to see which tools ran and which policies fired. Pair with app-level HTTP controls in the security guide and optional @hazeljs/​guardrails for content/PII filters.

Inspect before you ship

hazel gatekeeper validate
hazel gatekeeper simulate
hazel gatekeeper explain

These commands help you reason about policy without executing tools — useful in CI and incident reviews.

Cross-agent calls

Multi-agent setups do not get a free pass. @Delegate, supervisors, and A2A paths still go through Gatekeeper. “The other agent asked” is not authorization.

Read next