Hinge Dating Profile Optimizer

• Outcome: Pass
• Latest audit: May 28, 2026 at 12:54 PM UTC
• Version:
  0.1.0

Overview

This is an instruction-only dating profile coaching skill, with expected personal-data sharing risks but no evidence of code execution, exfiltration, persistence, or hidden behavior.

Safe to install as a text-based coaching skill if you are comfortable sharing dating-profile material with your agent. Share only what is needed, redact names, exact locations, third-party faces, private conversations, and sensitive identifiers, and treat its market/demographic advice as optional coaching rather than objective judgment.

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 (4)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill asks users to provide screenshots, photos, and settings from a dating profile, which can contain sensitive personal data such as face images, age, location, identity clues, and private preferences. Without an explicit privacy warning, minimization guidance, or instruction to redact third-party and unnecessary information, the skill increases the risk of oversharing sensitive data into the agent workflow.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: This skill explicitly solicits sensitive personal and dating-related information, including relationship goals, family setup, location habits, social patterns, and deal breakers, but the material shown does not provide a clear privacy notice, data handling explanation, retention policy, or minimization guidance. In a dating-profile context, aggregating these details can enable profiling, oversharing, or downstream misuse if users are not clearly warned what should not be shared and how their information will be used.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The flagged section presents gendered heterosexual dating-market claims as generalized strategic advice without strong scope limits, explicit user consent, or sufficient safeguards against stereotyping. In a profile-optimization skill, this can steer users toward biased self-assessments or exclusionary decisions, especially when framed as 'market reality' rather than optional, narrowly contextualized research interpretation.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The line "Shows they're not a loner" uses stigmatizing language about social status and frames social worth in an exclusionary way. In a dating-profile optimization skill, this can encourage biased or shaming judgments about users and others, creating policy and reputational risk even if the author likely intended practical advice about social proof.

VirusTotal

66/66 vendors flagged this skill as clean.