ClawHub
Back to skill

Security audit

AI Daily Briefing

Security checks across malware telemetry and agentic risk

Overview

This skill creates a daily productivity briefing from disclosed local productivity sources and does not install code, persist, mutate files, or send data elsewhere.

Install this only where the agent is allowed to read your task list, recent meeting notes, memory files, preferences, and connected calendar. Use explicit prompts such as 'daily briefing' in shared contexts, and keep sensitive notes out of the referenced folders if they should not appear in a briefing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases include broad, natural-language prompts like "what do I need to know?" and "what's today look like?" that can easily appear in ordinary conversation. This creates a real risk of unintended activation, causing the assistant to scan local files, meeting notes, memory files, or calendar data when the user did not explicitly intend to invoke this skill.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to read potentially sensitive sources including todo.md, meeting-notes/, MEMORY.md, session memory files, and calendar data, but it does not present a clear privacy warning or obtain informed user consent. If triggered unexpectedly or used by a user who does not understand the scope, it could expose personal schedules, confidential meeting content, or persistent memory data in the generated briefing.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill advertises multiple natural-language trigger phrases such as "what's on my plate?" and "start my day" that overlap with ordinary conversation. In assistant environments that route requests by phrase matching, broad triggers can cause accidental invocation, unexpected access to calendar/task context, or prompt-routing conflicts with other skills.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.