ClawHub
Back to skill

Security audit

Idea Validation

Security checks across malware telemetry and agentic risk

Overview

This is a plain-text business idea validation guide with no code, hidden access, or persistence, though its activation wording is broad.

Reasonable to install for structured startup or product idea review. Be aware it may trigger on broad market-research or competitor-analysis prompts, and avoid sharing confidential business plans, customer lists, or proprietary financial details unless you intend the agent to use them in the analysis.

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
95% confidence
Finding
The manifest description contains very broad trigger phrases such as 'market analysis', 'is this idea good', and 'market research', which can cause the skill to activate for many ordinary business or strategy queries beyond narrowly scoped idea validation. Over-broad activation is a real security and safety issue in agent systems because it increases unintended routing, prompt precedence conflicts, and the chance that this skill's strong behavioral framing ('ruthless but fair') overrides more appropriate domain-specific skills or default policies.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.