Women Who Love Too Much

• Outcome: Pass
• Latest audit: Jun 12, 2026 at 12:15 AM UTC
• Version:
  1.0.0

Overview

This is a text-only relationship self-help skill with no code execution or data access, but users should treat it as educational guidance rather than professional crisis, therapy, or abuse support.

Install only if you want book-based self-help guidance about codependency and relationship patterns. Do not rely on it for emergencies, domestic violence planning, self-harm, legal decisions, or medical or mental health treatment; use qualified professionals or local emergency resources for those situations.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• 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

Findings (5)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger list includes broad terms such as 'intimacy', 'attachment', 'recovery', and generic install/start phrases that can cause the skill to activate in unrelated conversations. In a sensitive mental-health-adjacent skill, unintended invocation can lead to unsolicited psychological framing, overconfident self-help guidance, or advice being injected into contexts involving abuse or crisis where more appropriate safety handling is needed.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill discusses abuse, addiction, toxic relationships, and emotional dependency but provides no upfront warning that it is educational self-help content rather than professional mental health, domestic violence, or crisis support. In this context, users may rely on the skill in situations involving coercion, danger, or severe distress, which increases the risk of harmful delay, misinterpretation, or inappropriate self-management.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The metadata frames the skill specifically around heterosexual women loving emotionally unavailable men, without indicating that this is a deliberately scoped audience or offering inclusive alternatives. In a psychology/relationship recovery context, that can exclude or misdirect users outside that demographic, and may cause the agent to deliver advice that is less appropriate or alienating for men, non-binary users, or same-sex relationship dynamics.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The content is explicitly framed around women pursuing men and presents the framework as generally applicable without stating that it is a book-specific, historically gendered lens. In a mental-health-adjacent recovery skill, this can exclude or misdirect users in other genders, sexual orientations, or relationship structures, reducing relevance and potentially causing harmful overgeneralization in sensitive situations.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The file repeatedly frames recovery and relationship guidance in explicitly gendered terms such as 'woman' and 'man' without offering inclusive alternatives or clarifying that the material is adapted from a women-specific source. In a mental health and relationship-support context, this can alienate users, misfit non-heterosexual or non-female users, and lead the agent to provide less appropriate guidance to vulnerable people seeking support.

VirusTotal

64/64 vendors flagged this skill as clean.