ClawHub
Back to skill

Security audit

The News

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only news lookup helper that uses a public API for current and archived headlines.

Install this if you want agents to use The Hear as a public headline snapshot and archive source. Treat returned headlines and AI overviews as news context rather than verified facts, and use additional sources for high-stakes or claim-specific verification.

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
89% confidence
Finding
The 'When To Use the Skill' section says to use the API whenever information about breaking news, real-time events, comparative analysis, global perspectives, or micro-historical data is needed. This is a very broad activation scope and does not provide concrete constraints, explicit trigger phrases, or negative examples to distinguish when the skill should and should not be invoked.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.