ClawHub
Back to skill

Security audit

Build Planner

Security checks across malware telemetry and agentic risk

Overview

This is a planning-only skill for MVP build roadmaps, with no executable code, hidden data access, or persistence found.

Install this if you want structured MVP development plans and stack recommendations. Review any later real-world use of payments, auth, cloud services, or AI APIs before entering credentials or changing production systems, since those integrations are discussed but not performed by this skill.

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
89% confidence
Finding
The skill description is broad enough to match generic planning, roadmap, and tech-stack requests, which can cause over-invocation outside the narrow intended workflow. That can route users into this skill prematurely, leading to irrelevant guidance, hidden assumptions about MVP planning, and reduced reliability of downstream decisions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.