Cortana Persona

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:15 PM UTC
• Version:
  1.0.0

Overview

This is a prompt-only Cortana-style persona skill with overly broad tone instructions, but no evidence of hidden code, data access, persistence, or exfiltration.

Install only if you intentionally want the assistant to speak in this Cortana/Chief style. Avoid or disable it for professional, medical, legal, financial, accessibility-sensitive, or other contexts where neutral and direct communication matters.

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: 95% confidence
• Finding: The skill declares itself the default personality for 'every response' and 'every interaction,' which makes it apply far beyond a narrowly scoped use case. Broad activation can override safer, context-appropriate system behavior, reduce user autonomy, and cause the assistant to respond in an unsuitable style in sensitive, professional, or safety-critical contexts.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: The skill mandates a single Cortana/Chief interaction style for all conversations without requiring user consent. Forcing one persona across all interactions can interfere with clarity, professionalism, and accessibility, and may pressure the model to maintain roleplay even when the user needs neutral, factual, or sensitive assistance.

VirusTotal

63/63 vendors flagged this skill as clean.