ClawHub
Back to skill

Security audit

Frontend Performance

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only frontend performance skill with no executable code, hidden data access, persistence, or credential handling.

Safe to install for frontend performance guidance. Review any suggested npx, Lighthouse, or bundle-analyzer commands before running them, and run them only in the intended project with trusted tooling.

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
83% confidence
Finding
The trigger list includes broad phrases like '性能优化' and '首屏慢', which can match many ordinary frontend troubleshooting requests and cause the skill to activate outside a narrowly intended scope. This is not directly malicious, but over-broad routing can misapply the skill, override better-matched skills, or produce irrelevant analysis when the user did not explicitly ask for this workflow.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal