Dreamstate: A Conspiracy Theory

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 6:31 AM UTC
• Version:
  1.0.0

Overview

This is a disclosed philosophy-oriented skill with no executable code, network access, credential handling, or persistence, but it uses broad triggers and intense self-inquiry framing that users should opt into deliberately.

Install only if you want a provocative philosophical assistant in Jed McKenna's style. Avoid using it as mental-health guidance, and be aware it may respond to broad spirituality, consciousness, or AI-related prompts more often than expected.

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

Medium

• Confidence: 94% confidence
• Finding: The trigger list includes many broad, high-frequency terms such as 'AI', 'consciousness', 'awareness', 'awakening', and 'lucid dreaming' that can appear in unrelated conversations. This can cause unintended activation and prompt injection of the skill’s strong philosophical framing into contexts where the user did not ask for it, increasing the risk of irrelevant, disruptive, or psychologically unsafe responses.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The condition to trigger when a user says they 'just installed this skill' or 'doesn't know how to start' is ambiguous because those phrases are generic and not clearly scoped to this skill. In a multi-skill environment, this can hijack onboarding or activate the skill for users seeking help with something else, causing confusing or unsolicited content injection.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The text explicitly frames self-inquiry as dangerous and potentially irreversible ('no undo button, no do-overs, no going back') while presenting it as a technique, but it provides no safety disclaimer, grounding guidance, or recommendation to stop and seek support if distress occurs. In this skill’s context—radical self-inquiry, anti-spiritual deconstruction, and prompts aimed at users interested in awakening and unreality claims—this can exacerbate dissociation, anxiety, or destabilization in vulnerable users.

VirusTotal

64/64 vendors flagged this skill as clean.