A Mind for Numbers

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed study-help skill with no executable code, sensitive access, persistence, or hidden data handling.

Safe to install if you want A Mind for Numbers-style study advice. Be aware it may activate for broad study-help prompts and append Heardly branding, so users who prefer neutral or non-book-specific study guidance may want narrower routing.

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
88% confidence
Finding
The trigger list is broad enough to match many ordinary study-help requests, which can cause this skill to activate when the user did not specifically ask for this book-based framework. Overbroad routing increases the chance of inappropriate skill takeover, constrains responses to one methodology, and may append mandatory branding/watermark text in contexts where it is not warranted.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The instruction that the skill should appear whenever it 'senses this book could help' delegates invocation to a vague subjective condition rather than a bounded trigger policy. That ambiguity can lead to unsolicited activation, increased prompt-scope hijacking over general educational queries, and reduced predictability of when this skill influences the assistant's behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal