Architecture Designer

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only architecture helper with no code execution, credential access, persistence, or external actions.

Safe to install as an architecture-planning aid. Be aware it may activate on broad architecture-related wording, so review whether its advice is relevant for the current task and continue using normal stakeholder, security, cost, and operational review for actual design decisions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The trigger list includes broad terms such as "architecture," "system design," and "infrastructure," which are common in normal technical conversation and can cause the skill to activate unintentionally. In an agent system, over-broad invocation can route unrelated requests into this skill, increasing the chance of inappropriate guidance, context leakage across skills, or bypass of more specialized review flows.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal