ClawHub
Back to skill

Security audit

daily-fintech-brief

Security checks across malware telemetry and agentic risk

Overview

This skill fetches listed public fintech and AI news sources, summarizes them, and saves local report/cache files in a disclosed workspace path.

Install this only if you are comfortable with the skill accessing the listed public news sites and keeping local archives. Delete or manage the OpenClaw workspace output directory if you do not want permanent report history, and treat cached-data reports as potentially one day stale.

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
90% confidence
Finding
The skill is designed to fetch remote content and persist both raw data and generated reports locally, including permanent report retention, but it does not present a clear user-facing warning or consent step before those data-affecting actions occur. In practice, this can surprise users, create unintended local data accumulation, and increase privacy and storage risk if fetched content contains sensitive or copyrighted material.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.