Share of Model Strategist

Security checks across malware telemetry and agentic risk

Overview

This is a coherent marketing strategy helper with no evidence of hidden access, data collection, persistence, or destructive behavior.

Safe to install for drafting Share of Model strategy. Users should treat the GEOly/geoly.ai references as branding or methodology unless independently verified, follow platform rules before editing public resources like Wikipedia or Wikidata, and use the actual included script path and arguments rather than the mismatched quick-start example.

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
93% confidence
Finding
The skill description includes broad trigger phrases such as 'dominating AI search in their category' and 'owning AI conversations,' which can match generic marketing requests well beyond a narrow Share of Model use case. This increases the chance of inappropriate skill activation, causing the agent to steer benign marketing conversations into GEO/AI-manipulation guidance and potentially produce off-target or policy-sensitive recommendations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal