ClawHub
Back to skill

Security audit

Ai Trends Reporter

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward AI news and ClawHub skill recommendation reporter, with disclosed network use and local installed-skill inspection that fit its purpose.

Install only if you are comfortable with the skill using Brave Search, optionally using a ClawHub token, and reading the names of installed OpenClaw skills to personalize recommendations. Review generated reports before sharing them because they may reveal your installed tooling.

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
93% confidence
Finding
The skill states in its workflow that it will scan the user's installed Skills directory, but this data access is not prominently disclosed as a user-facing warning before use. Even if the purpose is recommendation filtering, enumerating local installed skills exposes information about the user's tooling, workflows, and possibly sensitive interests, which can become privacy-sensitive when combined with network queries or reporting.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.