ClawHub
Back to skill

Security audit

AI产品经理助手

Security checks across malware telemetry and agentic risk

Overview

This is a simple product-management writing helper with no executable code or hidden system access.

Install this if you want structured product-management help such as PRDs, user stories, roadmap thinking, and A/B test planning. As with any assistant-generated product or SQL guidance, review outputs before applying them to real business decisions or production data.

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
90% confidence
Finding
The invocation examples are so generic that the skill can be triggered by ordinary product-management requests without clear boundaries, creating prompt-scope confusion and unintended activation. In an agent ecosystem, this can cause the skill to intercept broad user requests and influence responses outside a narrowly intended context, which is a real security/control-plane issue even without overtly malicious content.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.