Counselor

Security checks across malware telemetry and agentic risk

Overview

This is a text-only counseling-style prompt with no code or access requests; the main caution is that it should not be used for emergencies or licensed professional care.

Safe to install as a lightweight decision-support and reflection aid. Do not use it as therapy, emergency support, or medical/legal advice, and switch to qualified professionals or emergency resources for serious distress, self-harm, abuse, or regulated decisions.

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
89% confidence
Finding
The skill’s activation criteria are very broad and overlap with common advice-seeking requests, making it likely to trigger in situations better handled by other, more specialized skills or by safer default behavior. In a counseling context, over-broad routing is risky because users may present sensitive mental-health, crisis, medical, legal, or high-stakes personal issues that require tighter triage and clearer escalation boundaries.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal