kais-horse-en

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:42 PM UTC
• Version:
  1.0.0

Overview

This is an instruction-only philosophy skill; its broad always-on topic activation is worth noticing, but there is no evidence of code execution, data access, credential use, or destructive behavior.

Install this only if you want a philosophy companion that may activate during ordinary discussions about philosophy, consciousness, ethics, or AI. Prefer explicit /kh use or disable the skill if you do not want its cold speculative style or topic framing to appear outside direct commands.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (3)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger keywords include broad terms such as "philosophy," "paradox," "cognitive," "consciousness," and "AI ethics," which are common discussion topics rather than narrowly scoped invocation phrases. In a global skill, this creates a real risk of unintended activation or behavioral hijacking during ordinary conversation, causing the assistant to enter the skill's constrained mode when the user did not explicitly request it.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The skill is configured as global, high priority, and always_on, while also stating it should automatically link itself whenever philosophy-, consciousness-, ethics-, or AI-related topics arise. That combination makes activation boundaries ambiguous and overly expansive, increasing the chance that the skill overrides normal assistant behavior or injects its tone and constraints into unrelated conversations.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The guide states the skill auto-detects broad topics such as philosophy, AI, ethics, and consciousness, which creates an ambiguous activation condition that can trigger the skill in many normal conversations. This can cause unintended invocation, unexpected prompt injection into unrelated chats, and reduced user control over when the skill is active.

VirusTotal

64/64 vendors flagged this skill as clean.