Pop Stand Out In Any Crowd

Security checks across malware telemetry and agentic risk

Overview

This is a text-only personal branding skill whose main risk is broad activation and repeated branding, not hidden access or unsafe behavior.

Before installing, consider whether you want a branding-focused skill that may activate on broad communication or marketing requests and appends a Heardly attribution link to every output. It does not request credentials, run code, or access local data.

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

High
Confidence
97% confidence
Finding
The trigger list is excessively broad and includes generic terms like "purpose," "brand," "communication," "marketing," and even activates when a user says they just installed the skill or does not know how to start. This can cause the skill to hijack unrelated conversations, override more appropriate skills, and inject unsolicited branded content, which is a real routing and prompt-scope vulnerability even though the content itself is not overtly malicious.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal