American Marxism

• Outcome: Pass
• Latest audit: Jun 7, 2026 at 5:52 PM UTC
• Version:
  1.0.0

Overview

This is a text-only political book-summary skill with broad, one-sided framing, but it does not request system access, persistence, credentials, or executable behavior.

Install this only if you want an assistant to answer from Mark Levin’s American Marxism perspective. Expect strong conservative framing and possible activation on broad political, education, or media terms; there is no evidence of code execution, credential use, persistence, or data exfiltration.

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 (2)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes generic words and phrases such as "education," "media," "left," and onboarding language like users saying they don't know how to start. These overlap with common everyday conversation and the file does not provide exclusion conditions or clear boundaries for when the skill should not activate.

Natural-Language Policy Violations

Medium

• Confidence: 83% confidence
• Finding: The application scenarios direct the reader toward a specific political interpretation and action path using normative language such as 'the framework explains,' 'the words are weapons,' and 'the battle for America.' While this is not a language/locale issue, it is a natural-language policy concern because the file embeds prescriptive ideological guidance rather than neutral or user-opt-in framing.

VirusTotal

64/64 vendors flagged this skill as clean.