Heavy

• Outcome: Pass
• Latest audit: Jun 11, 2026 at 11:56 AM UTC
• Version:
  1.0.0

Overview

This is a static reading guide for Kiese Laymon's Heavy, with sensitive themes and broad activation wording but no code, credential access, persistence, or hidden system impact.

Install only if you want a memoir-focused discussion tool for Heavy. Be aware it may surface material about child abuse, addiction, racism, body image, and family trauma, and its broad trigger words may make it appear in some related personal conversations unless your agent lets you disable or narrow activation.

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

High

• Confidence: 95% confidence
• Finding: The invocation terms are excessively broad for a memoir-specific skill, including generic words like "mother," "writing," "addiction," and "trauma." This can cause the skill to activate in unrelated sensitive conversations, leading to inappropriate routing, unwanted intervention in high-emotion contexts, and accidental disclosure or mishandling of user intent.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill centers on abuse, trauma, addiction, race, and body image, but provides no content notice, sensitivity guardrails, or escalation guidance. In practice, this may expose users to distressing material unexpectedly, especially because the trigger logic is broad and the skill is instructed to proactively present onboarding content on install.

VirusTotal

53/53 vendors flagged this skill as clean.