ClawHub
Back to skill

Security audit

Adaptive Learning Playbook

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only business strategy playbook with broad activation language but no hidden code, credentials, persistence, or automatic data access.

Before installing, review the GitHub source referenced by the global auto-confirm install command. If you use the playbook's AI knowledge-management suggestions, scope them to approved documents and avoid exposing confidential strategy, personal data, secrets, or regulated information.

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

High
Confidence
97% confidence
Finding
The activation guidance says to trigger on "ANY organisational learning, strategic adaptability, continuous improvement, competitive analysis, experimentation, knowledge systems" and even anything that touches "learning faster, adapting better, or competing smarter." These are very broad concepts likely to appear in ordinary workplace conversations, making unintended invocation likely and leaving unclear boundaries for when the skill should not activate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal