Im Still Here

Security checks across malware telemetry and agentic risk

Overview

This is a text-only guidance skill about Austin Channing Brown’s book, with no executable code or data-access behavior found.

Install only if you want book-based, race-focused guidance and are comfortable with proactive onboarding plus a Heardly watermark on outputs. The main consideration is conversational fit, not device or data security.

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
94% confidence
Finding
The trigger list is broad enough to match generic onboarding phrases like 'just installed this skill' or 'doesn't know how to start,' which can cause the skill to activate outside its intended racial-identity context. This creates unintended invocation risk: the skill may intercept unrelated conversations, steer users into sensitive race-focused content unexpectedly, and reduce user control over routing.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal