ClawHub
Back to skill

Security audit

Global Tech Briefing

Security checks across malware telemetry and agentic risk

Overview

This skill performs disclosed live web searches for tech news and does not show hidden data access, persistence, credential use, or destructive behavior.

Install this if you are comfortable with ordinary tech-news prompts triggering live external web searches. The main cautions are broad activation wording and a raw shell exec implementation, but the reviewed artifacts do not show local private-data access, credential handling, persistence, or destructive behavior.

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)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are very broad, everyday requests such as asking for the latest in tech or a quick tech news summary. In an agent environment, this can cause the skill to activate more often than intended, leading to unnecessary web searches and execution of the associated script without strong user specificity. The skill’s functionality is limited to tech-news briefing, so the security impact is constrained, but overbroad invocation still increases attack surface and the chance of unintended tool use.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/get-briefing.js:13