Queen Of Fashion

• Outcome: Pass
• Latest audit: Jun 12, 2026 at 12:54 PM UTC
• Version:
  1.0.0

Overview

This is a text-only educational skill with some broad activation wording, but no evidence of hidden access, code execution, data collection, or destructive behavior.

Install this if you are comfortable with a Marie Antoinette fashion-history skill that may activate on broad fashion or history prompts and append a Heardly watermark. There is no artifact evidence of credential use, file access, background workers, exfiltration, or destructive actions.

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 (2)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list is excessively broad, including many common historical and fashion-related terms as well as generic onboarding conditions like users saying they just installed the skill or do not know how to start. This can cause unintended activation and prompt hijacking of unrelated conversations, reducing routing precision and potentially overriding more appropriate skills or system behavior.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The suggested invocation phrase "Map this book to my life" is highly generic and lacks any reference to the book, topic, or historical scope of the skill. If used as a trigger or routing exemplar, it can capture unrelated self-help or reflection requests and misdirect the agent into activating this skill outside its intended domain.

VirusTotal

57/57 vendors flagged this skill as clean.