ClawHub
Back to skill

Security audit

Data AI Daily Brief

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed daily-brief generator that searches public sources, writes report files, and can deliver them to configured channels after review.

Before installing, review `config.json` destinations and only enable channels you intend to use, since generated briefs may be sent to third-party services such as chat, email, or GitHub Pages using your configured credentials.

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
88% confidence
Finding
The skill is designed to push generated content to multiple external channels, but the skill text does not require an explicit user confirmation or a clear notice that data will leave the local workspace and be transmitted to third-party services. In practice, this can lead to unintentional exfiltration of sensitive or proprietary content if the brief includes internal notes, confidential context, or regulated information.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.