The Subtle Art of Not Giving a F*ck

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 3:24 PM UTC
• Version:
  1.0.0

Overview

This is a text-only self-help skill with broad activation and blunt book-based advice, but it does not include code, persistence, credential access, or data exfiltration behavior.

Install only if you want an opinionated, blunt self-improvement assistant based on this book. Do not rely on it for crisis, abuse, trauma, or mental-health treatment decisions, and expect promotional Heardly watermarking plus possible activation on broad topics like happiness, values, problems, or suffering.

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 (3)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list is very broad and includes generic phrases like "How to be happy," "problems," "values," and "happiness," which can cause the skill to activate for many unrelated conversations. This creates an invocation-scope vulnerability where the assistant may inappropriately route users into this skill, overriding more suitable guidance and increasing the chance of misleading or irrelevant advice.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The passage uses stigmatizing framing such as 'special snowflakes' and presents a single, unqualified explanation for anxiety and inability to handle criticism. In a self-help skill, this can shame users, discourage help-seeking, and cause harm to people with depression, anxiety, trauma histories, or other mental health conditions by recasting clinical or contextual problems as moral failings.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: The instruction to 'take responsibility for everything in your life — including the things that aren't your fault' is dangerously absolute in contexts involving abuse, coercion, discrimination, trauma, or systemic barriers. Users may internalize blame for harms done to them, remain in unsafe situations, or avoid seeking support because the skill frames all adversity as an individual responsibility problem.

VirusTotal

64/64 vendors flagged this skill as clean.