ask-user-md

Security checks across malware telemetry and agentic risk

Overview

This skill is a structured product-requirements interview helper with no executable code or hidden system access, though its activation wording is broad.

Install this if you want an opinionated product-requirements interview flow. Expect it to ask structured business and feature questions before drafting a requirements document; avoid sharing confidential business details unless they are needed for the planning task.

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 conditions include a catch-all phrase covering essentially any product-requirement-related expression, which is overly broad and can cause unintended activation outside the intended scope. In an agent setting, over-triggering can hijack normal conversations, cause incorrect workflow routing, and collect unnecessary user/business details when the user did not explicitly ask for structured requirement elicitation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal