AI Defense Stack

LLM firewalls & guardrails

HiddenLayer AI Runtime Security (AIDR): runtime threat detection module for AI apps

HiddenLayer AIDR is a runtime threat detection module for AI apps from HiddenLayer. It is a commercial product offered as: SaaS, On-prem, Self-hosted. Pricing model: not published.

  • Last reviewed
Visit HiddenLayer AIDR (opens in a new tab)
Commercial Layer 6: Runtime guardrails

Best for

Security teams that need runtime detection for AI apps and agents in on-premises or air-gapped environments

Consider instead if

  • You want an open-source library you can modify and run entirely yourself. See NeMo Guardrails.
  • You want a hosted guardrail API that your application calls directly. See Lakera Guard.

What HiddenLayer AIDR does

HiddenLayer AI Runtime Security, which a customer quote on the platform page calls AIDR, is a commercial module of the HiddenLayer AI security platform. Its product page covers prompt injection and indirect attacks, sensitive data exposure, unsafe agent actions and runtime visibility into agent workflows. Inline enforcement can detect, block or redact according to policy, and a separate AI Guardrails page describes output safety and content controls. The platform page calls it agentless and model-agnostic, and a 2025 HiddenLayer playbook lists on-premises, SaaS and air-gapped deployment. HiddenLayer shows no prices on the pages we opened, so ask the vendor about packaging and current product naming.

This summary is our own wording of the sourced facts on this page.

Key facts

Each value links to the page that states it, with the date we checked it.

Vendor
HiddenLayer Source, checked October 21, 2026: hiddenlayer.com (opens in a new tab)
Status
Active Source, checked October 21, 2026: hiddenlayer.com (opens in a new tab)
Open source
No: closed source (proprietary) Source, checked October 21, 2026: hiddenlayer.com (opens in a new tab)
Latest release
Not documented in the sources we checked
Deployment
SaaS, On-prem, Self-hosted Source, checked October 21, 2026: hiddenlayer.com (opens in a new tab)
Pricing model
Not published in the sources we checked Source, checked October 21, 2026: hiddenlayer.com (opens in a new tab)
Website
hiddenlayer.com Source, checked October 21, 2026: hiddenlayer.com (opens in a new tab)
Documentation
Not documented in the sources we checked
API reference
Not documented in the sources we checked
Quickstart
Not documented in the sources we checked
Security page
Not documented in the sources we checked
Attestations or disclosure
Not documented in the sources we checked

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Integrations

Where HiddenLayer AIDR fits in our AI security layers

Our analysis

Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.

AI security layers that HiddenLayer AIDR covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L6 Runtime Runtime guardrails Primary Screen what goes into and comes out of a model in live traffic, and limit abuse of the model endpoint. Follows its category, LLM firewalls & guardrails
L5 Data Data protection Also covers Documents blocking or redaction of sensitive data. Blocks or redacts sensitive information exposed in model interactions
L8 Monitoring Monitoring and response Also covers Documents sending runtime detections and enforcement events to SIEM, SOAR and security operations workflows. Sends runtime detections and enforcement events to existing SIEM, SOAR and security operations workflows

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to HiddenLayer AIDR, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM01 Prompt Injection Detects prompt injection and indirect attacks through retrieved content or tool output. Detects prompt injection and indirect attacks, including manipulation through retrieved content or tool output
LLM02 Sensitive Information Disclosure Inline controls can block or redact sensitive data exposure. Blocks or redacts sensitive information exposed in model interactions
LLM06 Excessive Agency Detects unauthorized agent behavior and malicious tool use. Detects unauthorized agent behavior and malicious tool use, with reconstructed agent interactions

Not mapped in our analysis: LLM05, LLM07, LLM09, LLM10. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in LLM firewalls & guardrails, ranked within the category by Coverage Score.

NVIDIA NeMo Guardrails

NVIDIA

Open sourceApache-2.0
  • Library
  • Self-hosted
  • API

Adds programmable input, dialog, retrieval, execution and output rails to LLM applications.

Best for: Teams that want to script rules for one LLM application in Python and run them in their own infrastructure

Coverage Score 76 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM05 Improper Output Handling
  • LLM06 Excessive Agency

Reviewed

Portkey AI Gateway

Palo Alto Networks (Portkey)

Open sourceMIT Freemium Now Prisma AIRS AI Gateway
  • SaaS
  • Self-hosted
  • API

Routes LLM traffic through one gateway API and runs input and output guardrail checks on each request.

Best for: Teams that want a single gateway for several LLM providers with guardrail checks, available as open source or as a hosted service

Coverage Score 69 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM05 Improper Output Handling
  • LLM09 Misinformation

Reviewed

Kong AI Gateway

Kong

Open sourceApache-2.0
  • Self-hosted
  • SaaS
  • API

Routes LLM traffic through Kong with prompt guards, PII sanitization, spend limits and observability.

Best for: Teams that already run Kong as an API gateway and want LLM routing and prompt controls on the same data plane

Coverage Score 65 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM10 Unbounded Consumption

Reviewed

HiddenLayer AIDR FAQ

Is HiddenLayer AI Runtime Security open source?

No. It is a commercial module of the HiddenLayer platform, and we found no public source repository for it.

Is AIDR the same as AI Runtime Security?

The platform page lists the module as AI Runtime Security and uses the term AIDR only in a customer quote, so confirm current naming with the vendor.

Where can HiddenLayer be deployed?

HiddenLayer's May 2025 AI Security Playbook says it offers on-premises, SaaS and fully air-gapped deployment options.

Key facts you can cite

We have no commercial relationship with HiddenLayer.

Sources & last reviewed

Last reviewed . We compile from the vendors' own public pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.