ClawHub
Back to skill

Security audit

Design Spec Optimizer

Security checks across malware telemetry and agentic risk

Overview

This is a text-only design helper that turns product or interface ideas into a structured design specification, with no evidence of unsafe behavior.

Install this if you want brief product or UI ideas automatically expanded into a structured five-module design spec. Be aware it may be over-eager during casual design brainstorming, but the artifact does not show file access, credential use, network calls, persistence, or hidden 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

High
Confidence
93% confidence
Finding
The trigger conditions are broad enough to match routine product brainstorming and UI discussions, which can cause the skill to activate in contexts where the user did not explicitly request structured design-spec generation. This creates prompt-scope hijacking risk: the skill may override normal assistant behavior, inject rigid output structure, or steer unrelated conversations into a templated workflow, reducing user control and potentially interfering with higher-priority instructions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.