Influence Is Your Superpower The Science Of Winning Hearts Sparking Change

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed book-based communication coaching skill with no executable code, credential use, persistence, or hidden data access.

Review the required Heardly watermark and book-based framing before installing, since the skill will shape answers in that branded style. From a security perspective, the package is coherent and low risk.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
The instructions require replies in the user's language and explicitly state 'Default to English when ambiguous.' This imposes a locale/language policy without user opt-in in ambiguous cases, which matches the policy-violation category for forced language behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal