ClawHub
Back to skill

Security audit

PRD Creator

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent PRD document generator with an optional local Word export script and no evidence of hidden data access or unsafe behavior.

Install if you want PRD drafting templates and optional Word export. Be aware that Word export runs a local Node script and uses the npm docx package, and use explicit prompts if you want to avoid the skill activating during general product discussion.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are broad enough to activate on generic product-design or documentation requests, which can cause the skill to run outside the user's intended scope. Over-broad activation increases the chance of unintended file access, package/script use, or prompt hijacking through unrelated conversations, especially because this skill advertises optional execution of a local conversion script.

Vague Triggers

Medium
Confidence
87% confidence
Finding
Ambiguous auto-activation examples such as requests to design a feature/module/product create a wide match surface and can misfire on ordinary advisory conversations. In context, this is more dangerous because the skill includes external dependency installation and a local Node-based export command, so accidental activation could lead to unnecessary tool usage or execution paths the user did not explicitly request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.