ClawHub
Back to skill

Security audit

RedHat Frontend Builder

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only frontend scaffolding skill with one metadata quality issue but no evidence of hidden data access, persistence, or malicious behavior.

Install only if you want an agent to scaffold or edit frontend project files. Review generated code and dependency choices before running it, keep secrets out of client-side code, and verify the publisher/branding if the RedHat name matters to your trust decision.

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
This manifest file declares a triggers section, but the value shown is a generic placeholder-like entry rather than a specific list of activation conditions. Without explicit trigger phrases, scope limits, or exclusion conditions, the skill's invocation behavior is unclear and could lead to unintended activation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal