ClawHub
Back to skill

Security audit

ai-daily-briefing

Security checks across malware telemetry and agentic risk

Overview

This daily briefing skill is purpose-aligned, but it needs review because broad prompts can automatically surface private tasks, meetings, calendar items, and memory context.

Review before installing. Use it only in workspaces where it is acceptable for the assistant to summarize tasks, meeting notes, calendar events, and memory files in chat. Prefer explicit invocations like "daily briefing" and disable or avoid calendar, memory, or meeting-note sources if they may contain confidential information.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list includes broad conversational phrases like "what do I need to know?", "start my day", and "give me the rundown," which can match ordinary user requests that were not intended to invoke this skill. In a skill that reads workspace files, meeting notes, memory files, and calendar data, accidental activation can expose sensitive information or cause the assistant to prioritize this skill over the user’s actual intent.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill states it pulls from todo.md, meeting-notes/, MEMORY.md, memory files, USER.md, and calendar sources, but it does not present a prominent user-facing warning that these may contain sensitive personal or business information. Users may invoke "briefing" without realizing the skill will aggregate and surface private content from multiple locations, increasing the risk of unintended disclosure in the response.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation describes pulling calendar events and to-do items into the briefing without any visible user-facing notice about what data is accessed, when it is accessed, or what permissions are required. This can lead users to expose sensitive scheduling, meeting, and task information without informed consent, increasing privacy and data-minimization risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.