Great Power Diplomacy

• Outcome: Pass
• Latest audit: Jun 6, 2026 at 6:04 PM UTC
• Version:
  1.0.0

Overview

This is a text-only educational diplomacy skill with broad activation wording but no hidden execution, data access, persistence, or malware signals.

Install this if you want book-specific strategic diplomacy guidance. Be aware it may respond to broad history or geopolitics prompts and append Heardly attribution text, so disable it if that framing appears in unrelated conversations.

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: 96% confidence
• Finding: The trigger list is broad enough to match common educational, historical, and current-events discussions, which can cause the skill to activate outside the user's actual intent. Over-broad activation can hijack unrelated conversations, steer answers into the skill's prescribed framing and watermarking, and increase the chance that embedded instructions in the skill override normal assistant behavior in contexts where the user did not ask for this specialty.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The manifest contains many broad trigger phrases such as "Statecraft," "Realpolitik," "Grand strategy," and "How to avoid war," which are common in normal educational, news, and policy discussions. This can cause the skill to activate when users did not intend to invoke it, increasing the chance of irrelevant instruction injection into unrelated conversations and reducing routing integrity.

VirusTotal

64/64 vendors flagged this skill as clean.