The Origin Of Consciousness In The Breakdown Of The Bicameral Mind

• Outcome: Review
• Latest audit: Jun 12, 2026 at 10:25 AM UTC
• Version:
  1.0.1

Overview

This is a content-only book-study skill, but it needs review because it activates very broadly and gives poorly bounded guidance about voices, hypnosis, and schizophrenia.

Review before installing if you want tight control over when skills activate or if users may ask about hallucinations, schizophrenia, hypnosis, dissociation, or mental-health distress. This skill is not malware, but it should be treated as a controversial book-analysis tool rather than health guidance.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger phrases and topic list are broad enough to activate on many ordinary conversations about consciousness, literature, religion, history, or neurology, causing the skill to hijack unrelated user requests. In an agent environment, overbroad activation can override more appropriate skills, inject unsolicited framing, and reduce user control over routing.

Vague Triggers

Medium

• Confidence: 98% confidence
• Finding: Triggering when a user says they just installed the skill or does not know how to start is excessively generic and can activate this skill even when the user is asking for unrelated help. This creates routing confusion and increases the chance of unsolicited, irrelevant responses being injected into the conversation.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: This section presents hypnosis as a practical technique and frames obedience to an external voice as a meaningful mental exercise without any safety caveat. In a skill about consciousness, inner voices, and altered mental states, that can encourage psychologically risky experimentation, especially for vulnerable users, and normalizes suggestibility without advising limits or professional caution.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The text discusses inner voices and schizophrenia in a way that can blur the line between ordinary self-talk and psychotic symptoms, and it includes the claim that the voices are not the pathology while offering no mental health warning. In this context, users experiencing hallucinations or delusional thinking could interpret distressing symptoms as spiritually or intellectually validated, which may discourage appropriate care or worsen confusion.

VirusTotal

64/64 vendors flagged this skill as clean.