ClawHub
Back to skill

Security audit

Newsflash

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent news briefing and alert integration, with disclosed local preferences and background alert behavior that users should understand before enabling.

Install this only if you are comfortable with a Newsflash CLI/API receiving your news topics and with the agent storing news preferences in the workspace. Enable recurring briefings or live alerts only when you want cron scheduling or a background stream, and delete newsflash.json or run the CLI logout flow if you no longer want local preferences or API credentials retained.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description includes broad invocation cues such as asks about news, headlines, markets, crypto, and what's happening, which can cause the agent to over-select this skill for loosely related requests. Over-broad routing increases the chance of unnecessary external tool use and unintended data disclosure to the news service, even though the underlying function is legitimate.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill instructs the agent to create and persist a local newsflash.json preferences file containing user interests, alert settings, and history without requiring a clear user-facing notice or confirmation before writing. This creates a privacy and transparency issue because user preference data is stored in the workspace by default and may persist longer than the user expects.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.