Skylv System Design

Security checks across malware telemetry and agentic risk

Overview

This is a system-design advice skill with broad activation wording, but it does not show hidden access, credential use, persistence, destructive actions, or executable behavior.

Install if you want architecture and scalability guidance. Be aware it may activate on broad engineering phrases; narrow or disable automatic triggers if it interrupts unrelated conversations.

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
94% confidence
Finding
The skill declares very broad auto-trigger phrases such as system design, architecture, distributed, and scalability, which are common in normal technical conversations. This can cause the skill to activate unintentionally, steering unrelated discussions into this skill’s behavior and increasing the chance of prompt hijacking, context pollution, or inappropriate tool/workflow selection.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal