The Hundred-Year Marathon: China's Secret Strategy to Replace America as the Global Superpower

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 1:21 AM UTC
• Version:
  1.0.0

Overview

This is a non-executable, opinionated book-summary skill with some overbroad triggers and biased phrasing risk, but no hidden code, data access, persistence, or privileged behavior.

Install only if you want an explicitly opinionated guide to this specific book. Expect strong U.S.-China strategic framing, and consider narrowing activation triggers or editing the blanket language claim before using it in general geopolitical discussions.

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 skill’s trigger list includes many broad geopolitical terms and common entities such as 'Xi Jinping,' 'Taiwan,' 'CIA,' 'DOD,' and 'South China Sea,' making accidental activation likely during unrelated conversations. This can hijack normal assistant behavior, force irrelevant ideology-laden content into responses, and increase the chance that users receive biased or unintended output outside the skill’s proper scope.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: Triggering when a user says they 'just installed this skill' or 'doesn't know how to start' is ambiguous because such phrases are common onboarding language that may appear in many contexts. Combined with the instruction that the AI 'MUST proactively present the Quick Start guide,' this can cause unsolicited activation and content injection even when the user did not request this specific subject matter.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: The statement "The Chinese language is inherently ambiguous" is a blanket characterization about a language and, by extension, its speakers. In this skill's geopolitical context, that framing can reinforce ethnic or national stereotyping and present contested political claims as linguistic fact, increasing the risk of biased or discriminatory output.

VirusTotal

63/63 vendors flagged this skill as clean.