ClawHub
Back to skill

Security audit

The News: Breaking News, Global News, & A Headline Archive

Security checks across malware telemetry and agentic risk

Overview

This documentation-only skill tells agents to query a public read-only news headline API and does not show credential use, file access, persistence, or destructive behavior.

Before installing, understand that news-related prompts may cause the agent to contact thehear.org and use returned headlines, links, and AI summaries. Treat the API output as a starting snapshot of media coverage rather than verified facts, and use additional sources for high-stakes claims.

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
87% confidence
Finding
The skill's activation guidance is broad enough that it could be invoked for many generic news- or current-events-related prompts, even when another tool or no tool would be more appropriate. This is not directly code-execution dangerous, but it can cause over-triggering, unnecessary external requests, and unintended data flow to a third-party API during normal agent operation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.