ClawHub
Back to skill

Security audit

Metacognition

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only thinking aid that gives metacognition coaching prompts and does not request system access, persistence, credentials, or automated actions.

This skill is reasonable to install if you want an agent to help structure reflection during hard problem-solving. Expect it to intervene in some conversations about calibration or reasoning quality; disable or ignore it when you want uninterrupted creative flow or routine task completion.

SkillSpector

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

Low
Confidence
91% confidence
Finding
The activation text says to activate when the user 'asks about calibration / thinking about thinking,' which is broader and less constrained than the other quoted phrases. Although some negative conditions are listed, this wording could overlap with ordinary reflective conversation and makes the invocation boundary less specific.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.