Understanding Women's Words Skill

• Outcome: Pass
• Latest audit: Jun 1, 2026, 5:44 AM
• Version:
  0.1.0

Overview

This is a non-executable relationship communication prompt with visible gendered framing, but it does not request system access, credentials, automation, or unsafe actions.

Install only if you are comfortable with a relationship-advice skill framed around women's messages. Treat its interpretations as possibilities, not facts, and use it to support direct, respectful clarification rather than to infer motives or manipulate someone.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

• Confidence: 89% confidence
• Finding: The skill is explicitly framed around 'women's words' and uses gendered examples like 'she wants to know your location,' which can normalize stereotype-based interpretation of communication. In a relationship-advice context, this is risky because users may overgeneralize gendered behavior, apply biased assumptions to real interactions, and receive lower-quality or unfair guidance despite the skill's stated anti-stereotyping goal.

VirusTotal

64/64 vendors flagged this skill as clean.