Performance Optimization

Security checks across malware telemetry and agentic risk

Overview

This is a coherent frontend performance review skill with no executable code, no credential handling, and only expected guidance to inspect performance evidence and write a report.

Install this if you want an agent to perform structured frontend performance analysis. Expect it to inspect relevant project files and possibly run performance or build commands when you ask for diagnosis, and to create a local report file under reports/.

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
85% confidence
Finding
The activation text is broad enough to match many routine frontend questions about slowness, bundle size, Lighthouse, or Web Vitals, which can cause this skill to trigger outside a narrowly scoped workflow. Over-broad activation increases the chance of inappropriate routing, unnecessary context injection, and user surprise, especially across multiple agent runtimes listed in the metadata.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal