Executive Coaching & Leadership Development Engine

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only executive coaching skill with sensitive workplace topics that are expected for its stated purpose and no hidden execution behavior.

Safe to install as a coaching reference. Use care with real workplace data: anonymize 360 feedback where possible, avoid entering unnecessary personal details, follow HR and privacy obligations, and keep human oversight for career-impacting decisions such as performance actions or succession planning.

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

Medium
Confidence
94% confidence
Finding
The skill exposes many broad natural-language commands such as 'Coach me on [topic]' and 'Help me with a difficult leader' that closely resemble ordinary user conversation. In agent systems that route by intent matching, these generic phrases can cause accidental invocation, unexpected context capture, or unreviewed execution of the coaching workflow when the user did not explicitly intend to call this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal