Skip to content
Security

AI security platform from identity to runtime

An AI security platform has to cover the whole path from the person or workload that signs in to the model, tool or agent that answers. Skyfix puts inspection inside the request path, not beside it, and keeps identity, keys, sessions and posture in the same console as the traffic they protect.

  • Inline AI Firewall and DLP
  • Enterprise identity
  • Zero-trust runtime
The AI Firewall protections card in the Skyfix console: prompt injection and jailbreaks, credentials and secrets, and system prompt leakage set to block; personal data and health information set to redact; harmful content set to block; each with the checks it applies to prompts or responses and an on switch.The AI Firewall protections card in the Skyfix console: prompt injection and jailbreaks, credentials and secrets, and system prompt leakage set to block; personal data and health information set to redact; harmful content set to block; each with the checks it applies to prompts or responses and an on switch.
AI Firewall protections. Per-workspace protections: block injection, secrets and harmful content; redact personal and health data.Illustrative synthetic data

One control plane

Where this sits in the request path

Inspection runs on input, output, streams, MCP and A2A with fail-closed holdback. External guardrail services can add a check but never replace it.

  1. Identity

  2. Policy

  3. AI Firewall

  4. Budget

  5. Route

  6. Evidence

01

Inline AI Firewall

The AI Firewall inspects prompts, responses, streamed chunks, MCP tool arguments and results, and A2A messages for prompt injection and jailbreaks, credentials and secrets, system prompt leakage, personal and health data and harmful content. Each protection is set per workspace to block, redact or monitor, and the action applies before a model or a caller sees the content. Detection content ships as signed packs your installation verifies and re-signs under its own keys, and findings open review cases in governance.

02

Enterprise identity

  • OIDC and SAML
  • SCIM
  • MFA

People sign in through your identity provider with OIDC or SAML, are provisioned and deprovisioned with SCIM, and can be required to use multi-factor authentication. Roles are scoped to the organization or to a workspace, and every permission that reads content, exports data or changes production is distinct, so a reader of traces does not automatically see prompts.

Directory, sign-in and roles are administered in the same console as keys and policy, which means an offboarding in your directory ends console access, API keys and approvals in one place.

03

Workload identity and mTLS

  • SPIFFE
  • Scoped keys

Workloads do not share human credentials. Applications use scoped API keys that carry allowed models, tools, environments, expiry and tags; services use workload identities and client certificates; and gateways enroll with their SPIFFE ID bound to the enrollment, so a gateway cannot be impersonated by copying a token. Keys are issued, rotated and revoked in the console, and every issue and revoke is audited.

04

Session, password and step-up policy

  • Defaults

Session policy is enforced by the server on every request: an idle timeout from 5 minutes to 12 hours, a session lifetime from 1 to 24 hours and a step-up window from 1 to 60 minutes, with a warning before expiry and a sign-in that returns you to the page you were on. Password policy sets length, history, lockout and always applies a blocklist of common and personal passwords. Step-up re-authentication is required only for high-risk operations: every console route is classified, and an unclassified route requires step-up by default.

The Identity controls card on Security › Posture in the Skyfix console: multi-factor authentication required for admins with a control to require it for everyone, a 12-hour session lifetime, a 2-hour idle timeout and re-authentication for sensitive changes after 15 minutes.The Identity controls card on Security › Posture in the Skyfix console: multi-factor authentication required for admins with a control to require it for everyone, a 12-hour session lifetime, a 2-hour idle timeout and re-authentication for sensitive changes after 15 minutes.
Identity controls. MFA requirement, session lifetime, idle timeout and the step-up window in one place.Illustrative synthetic data

05

Security posture findings

Posture evaluates identity, keys and AI assets continuously: people without MFA, keys without expiry, agents without a workload identity, tool servers with unreviewed catalogs. Each finding has a severity, evidence and a link to the asset, and feeds the readiness of every AI system that uses that asset. Snoozing or dismissing a finding is recorded in the audit trail with who did it and why.

  • Identity findings: MFA coverage, stale accounts, roles wider than their use.
  • Key findings: expiry, scope, unused keys and per-key reach across models and tools.
  • AI asset findings: agents, tool servers, workflows and skills missing an identity, review or owner.

06

Zero-trust runtime

The Helm chart installs with network policies that deny by default, so private destinations must be allowlisted and outbound traffic can be limited to approved addresses. Each workload has its own secrets-store role and reads only its own credentials; TLS is required outside development; and gateways authorize every request against a signed bundle they verified locally. During an incident the emergency deny switch and last-known-good bundles keep the fleet under control from a signed state.

No detection efficacy, block-rate or false-positive figures are claimed here. Console frames show illustrative synthetic data.

FAQ

Questions this page answers

What does an AI security platform cover?

The whole path: how people and workloads authenticate, which keys and scopes they hold, what the AI Firewall inspects inline, how sessions and step-up are enforced, what the posture findings say about your identity and AI assets, and how the runtime itself is locked down. Skyfix covers all of it in one console.

Which identity standards are supported?

OIDC and SAML for single sign-on, SCIM for provisioning, OAuth 2.1 for MCP client authorization, SPIFFE for gateway enrollment and mTLS between planes, plus scoped API keys and client certificates for workloads.

How is the gateway enrolled and authenticated?

A gateway enrolls with its SPIFFE ID bound to the enrollment and talks to the control plane over mTLS anchored on the installation CA. It verifies every bundle and directive it receives against your installation's signing keys.

What is step-up and when is it required?

Step-up is a fresh re-authentication within a configurable window, required only for high-risk operations such as publishing policy, exporting audit records or changing production. Every console route is classified; a route without a classification requires step-up by default.

What happens during an incident?

An emergency deny switch stops traffic for the scope you choose, last-known-good bundles let a fleet roll back in one signed action, gateways keep enforcing their verified policy if the control plane is unreachable, and every action taken is in the audit trail.