Detector catalog

The built-in TrustGuard detector catalog across data loss prevention, content security, and agent/MCP security.

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 (Agent Runtime) lists the catalog grouped by category, with a configuration form for each detector’s settings. Sensitivity (where exposed) maps to Permissive, Balanced (recommended), and Strict in the console.

Categories

Category	Focus
Data loss prevention	PII and secret detection + masking.
Content security	Jailbreaks, toxicity, moderation, document/URL analysis.
Agent & MCP security	Indirect prompt injection in tool-sourced content.

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).

Data loss prevention

Detector (slug)	Detects	Sides	Protocols	Mutable
data_loss_prevention	Sensitive PII (masked in flight) and secrets (API keys, access tokens, JWTs, Stripe keys) reported as findings.	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 (Moderation)	Off-topic / disallowed content via keyword+regex and/or NeuralTrust topics.	input, output	all	—
url_analyzer	Fetches URLs in the content (SSRF-guarded) and screens fetched text for indirect prompt injection and PII.	input	llm, mcp	—
doc_analyzer	Extracts text from uploaded documents (incl. OCR) and screens for PII and indirect prompt injection.	input	llm	—

Agent & MCP security

Detector (slug)	Detects	Sides	Protocols	Mutable
indirect_prompt_injection	Indirect prompt injection in tool-sourced content (e.g. role=tool / MCP tool results).	input, output	llm, 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.