ClawHub
Back to skill

Security audit

Research Automation

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only web research helper that openly searches the web and saves research notes, with no executable code or hidden install behavior found.

Install only if you want an agent to perform recurring or on-demand web research on these health-related topics and save markdown notes in your workspace. Enable heartbeat scheduling only if you want automatic searches and file creation, and verify any health or dosing-related claims against original medical or scientific sources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly describes automatic web research and auto-saving results, including scheduled heartbeat execution, but it does not clearly warn users that it will perform periodic network access and create files on disk. This can lead to unexpected external communications, unreviewed collection of potentially sensitive browsing/research context, and silent workspace modification, which is especially risky in an automated agent environment.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.