use-cases-page-generator

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable content-planning skill for use case pages, with only a minor privacy consideration around optional project-context files.

Safe for normal content-strategy use. Before installing, check that .claude/project-context.md and .cursor/project-context.md do not contain secrets or sensitive business details you do not want used in generated recommendations.

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 multiple broad natural-language triggers such as "for [role]", "by persona", and "by business goal," which are common phrases that can appear in many unrelated user requests. This can cause the wrong skill to auto-activate, leading the agent to apply inappropriate instructions, read project context unnecessarily, or steer outputs toward use-case-page generation when the user intended something else.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal