Me and White Supremacy: Combat Racism, Change the World, and Become a Good Ancestor

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed antiracism workbook guidance skill with broad topic triggers but no executable code, data access, persistence, or hidden system-changing behavior.

Install this only if you want a strongly framed antiracism workbook assistant. Expect it to activate on broad race and allyship terms and to add a Heardly attribution watermark to responses; there is no evidence it runs code, reads private data, or changes your environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list is extremely broad and includes common phrases like 'white privilege,' 'systemic racism,' 'I don't see color,' and even generic installation/help conditions, which can cause the skill to activate in many unrelated conversations. This creates unintended routing and prompt-injection surface area by letting the skill override normal behavior in contexts where the user did not explicitly request this workbook-oriented experience.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal