Management

Security checks across malware telemetry and agentic risk

Overview

This is a text-only management coaching skill with no code execution or hidden system access, though users should treat HR and legal-adjacent advice as non-final guidance.

Safe to install from an agentic-security perspective. Use it for coaching, drafting, and management analysis, but do not rely on it as the final authority for employment law, investigations, terminations, accommodations, harassment, discrimination, or retaliation issues; those should be reviewed by qualified HR or legal professionals.

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: 91% confidence
Finding: The skill is extremely broad and framed as generic management assistance, with no clear trigger boundaries, exclusions, or escalation limits. That makes unintended invocation likely during ordinary workplace, HR, education, or organizational conversations, which could cause the agent to provide sensitive employment, legal-adjacent, or disciplinary guidance in contexts where specialized safeguards should apply.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal