Build Managed It Services Provider Service Comparison Landing Page

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk, instruction-only marketing skill for drafting managed IT services landing-page content, with no code, credentials, persistence, or automatic actions.

Review any generated marketing copy for accuracy, pricing claims, compliance, and brand fit before publishing. Avoid putting sensitive customer details into prompts, and validate any separate publishing or automation workflow independently because this skill itself does not configure those actions.

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
90% confidence
Finding
The skill description and usage guidance are underspecified and overly broad, which can cause an agent to invoke the skill in contexts beyond its intended marketing use. This increases the chance of inappropriate automation, poor task routing, or generation of misleading business content without clear boundaries, especially because the workflow encourages producing a strong first draft before sufficient scoping constraints are defined.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal