ClawHub
Back to skill

Security audit

MECE (Mutually Exclusive, Collectively Exhaustive)

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only thinking framework for structuring problems with MECE decomposition and does not request risky access or perform actions.

Install this if you want the agent to apply MECE-style structured thinking. Be aware it may activate for broad problem-solving or presentation-prep requests, so users who prefer less structured brainstorming may want to invoke it explicitly rather than rely on automatic activation.

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 description mixes specific phrases like 'MECE' with vague conditions such as 'a problem feels too big to think about cleanly,' 'an analysis keeps going in circles,' and 'a presentation needs to survive hard scrutiny.' These are common, subjective situations without clear boundaries, so the skill may activate in many ordinary discussions where the user did not intend MECE-style decomposition.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The listed triggers include broad conditions like 'problem feels too big,' 'analysis is going in circles,' and 'presentation must convince hard-to-convince listeners.' While a short 'When NOT to use' section exists, it does not sufficiently disambiguate these everyday situations from cases that truly require this skill, leaving activation scope overly broad.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.