Safety & Security · Software component

Interaction Safety Scanner

Software componentSafety & SecuritySafety, Security & Governancearc:InteractionSafetyScanner

An automated assessment component that scans agent interactions for harmful language, prompt injection attempts, and sensitive information leakage.

Responsibility. Detects security and safety concerns in agent interactions.

Also known as: Policy violation detection

Direct neighbourhood (hover for relationship types)

Relationships

is invoked by dependency

Output Rail Ch7.1A

reads dependency

Trace Store Ch3.3

evaluates assurance

Agent Controller abstract Ch3.3

Classification

Technologies: LLM Guard
Quality attributes: Security (ISO/IEC 25010 | NIST AI RMF: secure and resilient)
Risks mitigated: Prompt injectionSensitive information leakageHarmful languageProfanityHate speechExplicit violenceSelf-harm encouragement

Sources

Ch3.3: T. Nguyen, "Web Navigation and Interaction Benchmarks," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 3.3. ISBN: 9798244538229.
Ch7.1A: T. Nguyen, "Advanced Implementation with Nvidia NEMO Framework and Nvlink," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.1A. ISBN: 9798244538229.