ClawHub
Back to skill

Security audit

Opc Project Screener

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Chinese-language consulting workflow for evaluating one-person-company startup projects and does not request dangerous system access.

Before installing, users should know this skill will guide detailed discussion of founder background, finances, risks, and business plans. Use it when you want a Chinese OPC/incubation screening workflow, and avoid sharing confidential business details unless you are comfortable providing them to the agent environment.

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
91% confidence
Finding
The skill description contains very broad trigger phrases such as general project screening, feasibility judgment, and startup evaluation terms. This can cause the skill to activate for ordinary business-advice conversations outside its intended scope, creating prompt-routing confusion and increasing the chance that users are steered into an unnecessary rigid workflow or that more suitable skills are bypassed.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill content is effectively Chinese-only and does not provide any mechanism to detect or honor the user's preferred language. This can cause incorrect activation behavior, reduced usability, and misunderstandings in multilingual contexts, especially if the surrounding agent or user operates in another language.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.