ClawHub
Back to skill

Security audit

Brand Profile

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed brand-profile setup helper that stores a local profile for later social-media work, with only a minor risk of activating on overly broad onboarding phrases.

Install this if you want a reusable local brand profile for social-media work. Be aware that generic onboarding requests may invoke it, so review whether the task is actually about brand setup before answering profile questions, and avoid placing sensitive private details in brand-profile.md unless downstream skills should reuse them.

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
89% confidence
Finding
The invocation cues are broad enough to match generic onboarding phrases like 'get started' or 'onboard,' which can cause the skill to activate outside the user's intended task. Because this skill is designed to run before other social-media skills and can redirect the workflow into profile setup, misrouting can disrupt normal operation, collect unnecessary business context, and crowd out the correct skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.