ClawHub
Back to skill

Security audit

First Principles Decomposer

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only reasoning skill that may activate broadly, but it does not ask for system access, credentials, network use, persistence, or unsafe actions.

Safe to install as a reasoning aid. Be aware that common phrases like 'break this down' or 'from scratch' may cause the agent to use this structured decomposition style when a lighter answer might have been enough.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list includes broad, natural-language phrases such as 'break this down', 'from scratch', and 'what are we assuming' that can occur in many ordinary conversations. This can cause unintended skill activation, leading the agent to shift into a decomposition workflow when the user did not explicitly request it, which can disrupt task routing and override more appropriate skills.

Vague Triggers

Low
Confidence
84% confidence
Finding
The 'When To Use' section is broadly scoped with guidance like 'Starting any new project or initiative' and 'Feeling stuck on a complex problem,' which lacks operational boundaries. Ambiguous scope increases the chance of overuse or misapplication, causing the agent to invoke this skill in contexts where it adds noise, delays, or distracts from domain-specific handling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.