ClawHub
Back to skill

Security audit

Multi Search

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed research-assistant skill that uses web retrieval and subagents to create local markdown research reports, with no evidence of hidden execution, credential access, deletion, or exfiltration.

Install this if you want an automated multi-topic research workflow that may run several web-research agents and save markdown reports locally. Before using it, choose a clear output location and avoid pasting sensitive or private material unless you are comfortable with it being passed to subagents and stored in generated files.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill automatically detects or creates output directories and writes multiple research documents to disk, but the user-facing description and trigger guidance do not clearly warn about this side effect before invocation. In an agent environment, undisclosed filesystem writes can surprise users, overwrite or clutter project directories, and create artifacts in sensitive workspaces, especially because the output path selection includes the current working directory as a fallback.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.