First Principles Decomposer

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only reasoning skill that teaches a first-principles problem-solving workflow and does not request system access, credentials, network use, or persistent behavior.

This appears safe to install as a reasoning aid. Be aware that its broad trigger phrases may steer some ordinary requests into a structured decomposition format, and review its recommendations before acting on them in important business, financial, legal, or safety-sensitive decisions.

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 trigger list includes broad, natural-language phrases such as "from scratch," "break this down," and "what are we assuming" that can occur in ordinary user requests. This can cause unintended skill invocation, steering conversations into a decomposition workflow when the user did not explicitly request it, which may disrupt task routing or override more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal