New York City

Security checks across malware telemetry and agentic risk

Overview

This is a coherent NYC guidance skill with disclosed optional local memory and no executable install behavior.

Before installing, be comfortable with optional local notes in ~/new-york-city/ about boroughs, neighborhoods, commute constraints, budget pressure, timelines, and open tasks. Use stateless mode if you do not want files created, and do not store credentials, payment details, passport numbers, account numbers, or full street addresses in the memory file.

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
92% confidence
Finding
The setup instructs the skill to activate "whenever the user mentions New York City at all," which is broader than necessary for the stated domain. Over-broad activation can cause unintended routing, collection of user context for marginal mentions, and accidental persistence prompts in conversations where NYC is incidental rather than the main task.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal