TrustGuard ships a fixed catalog of detectors. You don’t build a detector
from scratch — you pick one from the catalog, configure its settings, then
reference the detector you created from a
policy. This page is the index of what’s
available; each catalog detector’s full settings live on its category page
(linked below).
The console’s Detectors → Catalog lists the catalog grouped by category,
with a configuration form for each detector’s settings.
Categories
| Category | Focus |
|---|
| Application security | Dangerous code/injection patterns in the request. |
| Data loss prevention | PII and secret detection + masking. |
| Content security | Jailbreaks, toxicity, moderation, document/URL analysis. |
| Behavioral security | Abusive‑actor and anomaly detection across requests. |
| Agent & MCP security | Jailbreaks planted in an agent’s own definition. |
The catalog
Each catalog detector is identified by a stable slug. Sides = which
directions it supports. Mutable detectors can rewrite the payload (so they
support the Transform action).
Application security
Detector (slug) | Detects | Sides | Protocols | Mutable |
|---|
code_sanitation | Dangerous code‑injection patterns by language (JavaScript, Python, PHP, SQL, shell, HTML) + custom patterns. | input | all | — |
Data loss prevention
Detector (slug) | Detects | Sides | Protocols | Mutable |
|---|
data_loss_prevention | 43 PII entities and 4 secret types (API keys, access tokens, JWTs, Stripe keys); masks them in flight. | input, output | all | ✅ |
Content security
Detector (slug) | Detects | Sides | Protocols | Mutable |
|---|
prompt_guard | Jailbreaks / prompt injections, scored by the NeuralTrust Firewall. | input, output | all | — |
toxicity | Toxic content, scored by the NeuralTrust Firewall. | input, output | all | — |
prompt_moderation | Off‑topic / disallowed content via keyword+regex and/or NeuralTrust topic probability. | input, output | all | — |
url_analyzer | Fetches URLs in the content (SSRF‑guarded) and screens them for jailbreaks and PII. | input | llm, mcp | — |
doc_analyzer | Extracts text from uploaded documents (incl. OCR) and screens for PII and jailbreaks. | input | llm | — |
multiturn_guard | Multi‑turn jailbreaks that build up across a session_id. | input | all | — |
multiturn_guard is functional but hidden from the catalog picker by default.
Contact NeuralTrust to enable it for your team.
Behavioral security
Detector (slug) | Detects | Sides | Protocols | Mutable |
|---|
anomaly_detector | Abusive actors keyed on consumer_id: bot‑like timing, repeated payloads, escalation, cross‑collector abuse. | input | all | — |
Agent & MCP security
Detector (slug) | Detects | Sides | Protocols | Mutable |
|---|
tool_guard | Jailbreaks/injections planted in the agent’s own system prompt and tool descriptions. | input | mcp | — |
How the catalog, detectors, and policies fit together
- A catalog detector is a fixed capability — you can’t change its code, only
its settings.
- A detector is a named, reusable instance
you create from a catalog detector plus its settings. It is detection‑only.
- A policy references detectors in rules
that set the action (Monitor / Block / Transform) and the
evaluation phase (Input / Output).
- Only
data_loss_prevention is mutable — the only catalog detector where
Transform is valid and the only one that can populate transformed_payload.
Next: configure a detector, compose a
policy, attach it to a
collector, and inspect traffic with the
Guard API. 
