Difficult Conversations

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:29 PM UTC
• Version:
  1.0.0

Overview

This is a text-only coaching skill for preparing difficult conversations, with safety caveats and no evidence of hidden execution or data collection.

Reasonable to install for general conversation preparation. Treat workplace, legal, medical, abuse, or safety-related suggestions as coaching, not professional advice, and use qualified help or emergency resources when threats, retaliation, or legal disputes are involved.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill description is broad enough to trigger on many ordinary requests for advice about work, family, partners, or conflict, which can cause the agent to over-invoke this skill outside clear user intent. That increases the chance of unwanted steering into scripted interpersonal guidance, including in situations involving abuse, retaliation, or legal/employment sensitivity where more careful routing or safety screening is needed.

VirusTotal

62/62 vendors flagged this skill as clean.