ClawHub
Back to skill

Security audit

LAC CreativeRules

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk, instruction-only LAC POWER brand guideline skill with one minor routing concern around broad trigger phrases.

Install this only if you want LAC POWER-specific brand guidance. Verify that the referenced logos, product images, wiring diagrams, and product-spec files are available from a trusted source, and be aware the skill may need narrower activation rules so it does not influence unrelated design requests.

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
90% confidence
Finding
The trigger list contains generic design phrases like 'brand guidelines', 'design standards', and 'compliance check' that are not scoped to LAC POWER or this specific asset set. This can cause the skill to activate for unrelated user requests, leading to unintended instruction injection into broader conversations and incorrect or overly authoritative design guidance being applied outside its intended context.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.