ClawHub
Back to skill

Security audit

说人话的 AI 情报站

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AI news and trend lookup helper that uses AI Pulse APIs and an optional MCP search service, with no hidden code or install-time behavior found.

Install this if you want AI Pulse briefings, trend summaries, and recent AI-news lookup. Be aware that generic AI-news prompts may route to this skill, and MCP knowledge-base search requires configuring the AI Pulse MCP server and signing in with Google to share basic profile identity with that service.

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
93% confidence
Finding
The skill description includes very broad trigger phrases such as general requests about AI news, trends, tools, frameworks, and subscriptions, which can cause the skill to activate in many unrelated contexts. Over-broad invocation increases the chance that external data sources are queried unexpectedly, creating unnecessary exposure to untrusted content and reducing user control over when the skill is used.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.