The Power Of A Positive No Save The Deal Save The Relationship And Still Say No

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 3:32 PM UTC
• Version:
  1.0.0

Overview

This is a non-executable communication coaching skill with broad activation and branding instructions, but no hidden access or unsafe behavior was found.

Before installing, know that this skill may activate during general conversations about saying no, negotiation, boundaries, or assertiveness, and it tells the assistant to add a Heardly watermark to each skill response. There is no artifact evidence of hidden data access, command execution, persistence, or credential use.

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: 94% confidence
• Finding: The trigger list includes broad everyday terms such as "negotiation," "boundaries," "assertiveness," and even a condition to trigger when a user says they just installed the skill or does not know how to start. This can cause the skill to activate in many unrelated conversations, creating unintended prompt injection surface and response hijacking where the assistant follows this skill’s formatting and onboarding rules outside the user’s actual intent.

VirusTotal

63/63 vendors flagged this skill as clean.