ClawHub
Back to skill

Security audit

Content Pillars

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward content-strategy skill that reads local brand materials and writes a content-pillars file, with only a minor chance of activating too broadly.

Installers should expect this skill to read local brand strategy files and create content-pillars.md. If a request uses the word "pillars" outside marketing or content strategy, confirm intent before relying on the skill's output.

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
86% confidence
Finding
The trigger list includes broad terms such as "pillars" and "content strategy," which can plausibly appear in many unrelated user requests and cause the skill to activate outside its intended scope. Over-broad activation increases the chance of incorrect tool/skill selection, pulling in brand-profile data or steering the conversation into artifact generation when the user did not ask for this skill specifically.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.