ClawHub
Back to skill

Security audit

Scamper

Security checks across malware telemetry and agentic risk

Overview

This is a simple brainstorming skill that guides SCAMPER idea generation and only describes a disclosed, user-confirmed note-appending workflow.

Install this if you want SCAMPER-style brainstorming help. Be aware it may offer to save generated ideas into notes/ideas.md; approve that only when you want the output persisted.

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
88% confidence
Finding
The skill description is broad and includes multiple vague triggers such as 'develop/expand an idea,' 'when stuck,' and 'processing new ideas,' which can cause the agent to invoke this skill in situations where SCAMPER was not explicitly requested. Over-broad activation increases the chance of unintended behavior, context switching, or overwriting a more appropriate skill choice, especially in automated workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.