The Hundred Years' War on Palestine: A History of Settler Colonialism and Resistance, 1917–2017

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 12:17 AM UTC
• Version:
  1.0.0

Overview

This is a disclosed, text-only history skill with no executable code or data access, though users should know it presents a specific Palestinian/Khalidi framing and may activate on broad topic terms.

Install this if you want a guided summary of Khalidi's book and its Palestinian settler-colonial framework. For neutral research or debate preparation, compare it with other historical perspectives, and be aware that broad topic mentions may invoke this skill's framing.

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: 94% confidence
• Finding: The trigger list is extremely broad and includes many common topical terms such as 'Palestine,' 'Gaza,' 'Jerusalem,' and 'occupation,' which can cause the skill to activate in conversations where the user did not intend to invoke this specific book-framed perspective. In a politically sensitive domain, unintended invocation can bias responses, override user intent, and create prompt-routing conflicts with other skills or general-purpose assistant behavior.

Vague Triggers

Low

• Confidence: 83% confidence
• Finding: The instruction to proactively present the Quick Start when the user 'just installed this skill' or 'doesn't know how to start' is ambiguous and may cause unsolicited behavior without a clear user request to use this skill. While not directly enabling code execution or data theft, it can lead to unwanted activation and response hijacking, especially when the assistant is expected to remain neutral until the user chooses a tool.

VirusTotal

64/64 vendors flagged this skill as clean.