ClawHub
Back to skill

Security audit

ai-newsletter-daily

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward AI news digest generator with disclosed web-search behavior and only optional file output.

Installers should know this skill will search the live web and may fetch article pages to build a digest. Choose inline output unless you want a markdown file saved to persistent output storage.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The invocation text is intentionally broad enough to trigger on generic requests like 'more AI news' or 'catch me up on AI,' not just explicit newsletter requests. That can cause the agent to select this skill in situations where the user did not clearly consent to live web search, ranking, and possible file-writing behavior, increasing the risk of overreach and unexpected actions.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill can write a markdown file to persistent user storage and present it, but the description does not clearly warn users of that capability up front. If the skill is auto-invoked, users may be surprised that their request resulted in data being saved, which creates consent, privacy, and data-retention concerns.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.