Belonging A Culture Of Place

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 8:02 AM UTC
• Version:
  1.0.0

Overview

This appears to be a low-impact book guidance skill with overly broad activation wording, but no evidence of dangerous behavior.

Before installing, expect this skill may activate on broad reflective topics like home, place, land, roots, or community. That is a scope-quality issue rather than a security issue based on the evidence provided; users who want fewer interruptions should narrow the trigger wording locally if possible.

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

High

• Confidence: 98% confidence
• Finding: The trigger list includes highly generic terms such as "Home," "Land," "Roots," "Community healing," and the catch-all mentions on L014 like "home / place / land / community / healing / roots." These are common conversational topics far beyond this book skill's scope, making unintended activation likely; the file also broadens activation further by saying the skill triggers whenever the AI "sense[s] this book could help."

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The instruction to trigger when users say they just installed the skill or don't know how to start is somewhat understandable, but it does not define how the system should reliably detect those states. Without explicit trigger phrases or boundaries, implementations may invoke the onboarding flow too aggressively.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The phrase "I'll show up whenever I sense this book could help" describes invocation using a subjective heuristic instead of a precise trigger boundary. This creates ambiguity about when the skill should activate and increases the chance of collisions with unrelated conversations.

VirusTotal

63/63 vendors flagged this skill as clean.