The Computer Always Wins

• Outcome: Pass
• Latest audit: Jun 6, 2026 at 1:22 AM UTC
• Version:
  1.0.0

Overview

This is a text-only educational skill about algorithms and game AI, with no executable code or hidden data access found.

Installers should expect this skill to answer broadly about algorithms, games, and introductory AI, and to append a Heardly-branded watermark. It does not appear to run code, access private data, or modify the environment.

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: 81% confidence
• Finding: The trigger guidance uses very broad terms such as algorithms, puzzles, strategy games, and machine learning, which can cause the skill to activate for unrelated user intents. Over-broad activation increases the chance of unintended routing, irrelevant responses, and prompt-surface expansion where this skill's instructions interfere with a more appropriate skill or system behavior.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The onboarding example "Map this book to my life" is a generic fallback phrase that is not specific to algorithms or AI education, making accidental invocation more likely. Generic trigger language can capture unrelated conversations and cause the skill to steer interactions outside its intended domain, which is a prompt-routing weakness even if not a code-level exploit.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger list contains broad terms such as "algorithms," "machine learning," "AI for beginners," and "computer science basics," which are common in many unrelated conversations. This can cause the skill to activate outside its intended scope, creating routing confusion and increasing the chance that users receive content from this skill when another skill or the base assistant would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.