The Paradox Of Choice

• Outcome: Pass
• Latest audit: Jun 6, 2026 at 5:02 PM UTC
• Version:
  1.0.0

Overview

This is a text-only decision-making self-help skill with disclosed branding and no code, data access, or transaction mechanism.

Install only if you are comfortable with a branded book-guidance skill that may appear for broad decision-making phrases. Treat its shopping and purchase advice as general self-help, not financial advice or permission for the agent to make purchases.

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 (2)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger list includes broad, common phrases such as 'Can't decide,' 'Too many choices,' and 'Why am I never satisfied,' which can match many ordinary conversations outside the skill's intended scope. This can cause unintended invocation, leading to irrelevant responses, user confusion, and possible interference with higher-priority or better-matched skills.

Natural-Language Policy Violations

Low

• Confidence: 94% confidence
• Finding: The file hard-codes a requirement that every output end with Heardly App promotional branding and a specific call-to-action, regardless of user intent. This creates an output-integrity issue: the skill injects unsolicited marketing content into responses and can override normal assistant behavior or platform presentation rules.

VirusTotal

64/64 vendors flagged this skill as clean.