Models: Attract Women Through Honesty

• Outcome: Review
• Latest audit: Jun 9, 2026 at 9:24 AM UTC
• Version:
  1.0.0

Overview

This is a coherent dating-advice skill with no executable code, but it should be reviewed because it gives physical-escalation advice without adequate consent safeguards.

Install only if you specifically want a Mark Manson 'Models' style dating-advice skill. Review its advice critically, especially around kissing, sex, and physical escalation: users should prioritize clear consent, respect hesitation or refusal immediately, and avoid treating gendered claims as universal rules.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (8)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list is excessively broad and includes many generic relationship, confidence, geography, and self-improvement terms, making accidental activation likely in unrelated conversations. Overbroad routing can hijack user intent, inject unsolicited dating/manipulation guidance, and bypass user expectations about which skill should respond.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Configuring the skill to trigger when a user says they just installed it or do not know how to start is an ambiguous activation condition that is not specific to this skill's subject matter. This can cause unsolicited takeovers of onboarding-style conversations and steer users into dating advice without a clear request, increasing the risk of inappropriate or context-mismatched responses.

Natural-Language Policy Violations

Medium

• Confidence: 86% confidence
• Finding: The instruction 'Men Must Lead' combined with 'escalating physically' and 'not seeking permission' promotes gendered, normative dating behavior without contextual safeguards or consent framing. In a relationship-advice skill, this is risky because users may interpret it as guidance to ignore explicit verbal consent norms, which can encourage coercive or boundary-crossing behavior.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The metadata frames the skill explicitly around men attracting women and reinforces a narrow heterosexual, gender-specific model without offering inclusive alternatives or user choice. In a relationship-advice skill, this can cause exclusion, misapplication of advice to users outside the intended demographic, and normalization of biased assumptions about gender and attraction.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The content presents broad claims about what women universally want and how men should behave as factual guidance without qualification or context. In a dating-advice skill, this can reinforce harmful stereotypes, normalize manipulative or non-consensual framing such as 'leading' over explicit consent, and misguide vulnerable users seeking interpersonal advice.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The text frames a gender-specific, heterosexual dating model as a general rule set, which can mislead users into applying narrow social assumptions as universal advice. In a skill that is triggered for broad dating-help queries, this increases the risk of exclusionary or distorted guidance and can reinforce harmful stereotypes about gender roles and attraction.

Natural-Language Policy Violations

High

• Confidence: 98% confidence
• Finding: The statement that asking 'Can I kiss you?' is needy and that men should escalate physically discourages verbal consent and normalizes initiating physical contact without explicit permission. In a dating-advice skill, this is especially dangerous because users may operationalize it in real interactions, increasing the risk of boundary violations, coercive behavior, and unsafe or non-consensual physical escalation.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The skill is explicitly framed around teaching men how to attract 'women' and repeatedly presents gender-specific assumptions as the default, without offering inclusive alternatives or documenting a legitimate scope constraint. In a relationship-advice skill, this can reinforce stereotyping, exclude users with different sexual orientations or gender identities, and cause the assistant to apply mismatched advice in ways that reduce safety and appropriateness.

VirusTotal

VirusTotal findings are pending for this skill version.