ClawHub
Back to skill

Security audit

Personal Board Of Directors

Security checks across malware telemetry and agentic risk

Overview

This is a text-only decision-support skill that structures advice from five fictional advisors and does not request sensitive access or execute code.

Install this if you want a structured decision-making prompt. Be aware it may activate on broad phrases like asking for help deciding; review the output critically and avoid sharing sensitive personal or financial details unless needed for the 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
90% confidence
Finding
The description includes broad activation phrases such as 'help me decide,' 'pressure-test this decision,' and 'what would smart advisors say,' which can overlap with ordinary conversation and unintentionally trigger the skill. While the skill itself is not overtly dangerous, unexpected invocation can steer conversations into a structured decision workflow the user did not explicitly request, reducing predictability and potentially influencing outcomes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.