ClawHub
Back to skill

Security audit

prd-development

Security checks across malware telemetry and agentic risk

Overview

This skill is a PRD-writing workflow with no executable code or hidden system access, though it may route work to other named skills.

This appears safe to install as a document-writing assistant. Before using it with sensitive product plans or meeting notes, review any referenced downstream skills such as DNS-analysis, botnet-analysis, and docx_handler because this skill may hand work to them during the workflow.

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 trigger description is broad enough to activate on generic phrases like '写PRD', '用户故事', or '功能说明', which can cause the skill to run outside its intended scope. Over-broad invocation increases the chance of misrouting user requests, auto-loading downstream domain skills incorrectly, and causing unintended document-generation actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.