ClawHub
Back to skill

Security audit

pm-chen

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed product-planning workflow that creates design, prototype, PRD, API, and handoff artifacts with user review gates.

Install this if you want a Chinese-first product handoff workflow. Be aware it may activate on general product design or prototype requests, and it may use connected Feishu/Tencent document tooling to create or update handoff docs when available.

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
91% confidence
Finding
The activation criteria are broad enough to capture a wide class of ordinary product, prototype, PRD, and handoff requests, which can cause the skill to take over conversations without strong user intent or precise scope matching. In an agent environment, this increases the risk of misrouting tasks, unnecessary artifact generation, and unintended use of downstream tools or connected skills before the user explicitly wants this workflow.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.