ClawHub

LaunchFast Full Research Loop

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a normal product-research workflow, but users should be aware it sends business research inputs to external services and saves an HTML report locally.

Before installing, treat product ideas, ASINs, supplier details, and sourcing strategy as potentially sensitive because they may be sent to external research services. When generating the report, use a specific non-sensitive output path, avoid overwriting existing files, and open the HTML report with normal caution if it contains third-party data.

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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to save a standalone HTML file directly to a user-specified path, with a default path under Downloads, but does not require explicit confirmation before local file creation or warn about overwrite risk. In an agent setting, writing files to disk can surprise users, overwrite existing files, or create artifacts containing sensitive research data without the user's informed consent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill sends user-provided keywords, optional competitor ASINs, and sourcing-related inputs to multiple external MCP services without any notice that this data will be shared externally. Even if the data seems business-oriented, it may include proprietary product ideas, market strategy, or sensitive commercial research that users would reasonably expect the agent to handle transparently.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal