The New Economics

Security checks across malware telemetry and agentic risk

Overview

This is a management-advice skill about Deming's The New Economics, with no executable code or data-access behavior, though its activation and promotional watermark instructions are broad.

Safe to install if you want Deming-based management and quality advice. Be aware that it may proactively present onboarding text and append Heardly promotional attribution even when a question is only loosely related.

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: 94% confidence
Finding: The instruction that the skill should appear whenever the AI 'senses this book could help' creates an open-ended activation boundary that can match many ordinary management, motivation, quality, or onboarding conversations. Overbroad triggering is dangerous because it can cause unsolicited skill takeover, crowd out more relevant skills or baseline behavior, and make the agent follow this skill's formatting and routing rules in contexts the user did not clearly intend.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: Triggering when a user 'just installed this skill' or 'doesn't know how to start' is ambiguous because those phrases commonly appear in generic onboarding flows unrelated to Deming or management advice. This increases the chance that the skill activates outside its domain and injects its mandatory Quick Start content into unrelated interactions, which is a scope-control and prompt-routing weakness.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal