The Road To Unfreedom

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 5:40 AM UTC
• Version:
  1.0.0

Overview

This is a text-only educational skill about Timothy Snyder’s book and disinformation frameworks, with no code execution, credential access, persistence, or data movement.

Before installing, be aware that this skill may steer broad conversations about truth, media, politics, or manipulation into the book’s framework and will append a branded Heardly watermark to responses. It appears safe from a security standpoint, but users who want neutral political discussion may prefer to invoke it only when they explicitly want this book-centered lens.

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

Medium

• Confidence: 90% confidence
• Finding: The skill declares very broad trigger phrases such as generic statements about truth, media, politics, and manipulation. This can cause the skill to activate in ordinary conversations that are only loosely related to the book, creating unintended routing, overcollection of context, or inappropriate ideological framing in responses.

Vague Triggers

Low

• Confidence: 80% confidence
• Finding: The rule to trigger when a user 'just installed this skill or doesn't know how to start' is underspecified and can be interpreted inconsistently by the agent. That ambiguity increases the chance of unsolicited activation and unexpected proactive messaging, especially in onboarding or general help contexts.

VirusTotal

64/64 vendors flagged this skill as clean.