ClawHub
Back to skill

Security audit

Bedtime Story Teller

Security checks across malware telemetry and agentic risk

Overview

This bedtime-story skill is coherent and local-only, with disclosed story generation, optional TTS, local history/settings storage, and an optional daily cron reminder.

Before installing, decide whether you want the optional daily cron reminder. If you use it, review your crontab afterward and know how to remove the entry. Consider narrowing the trigger phrases if ordinary family conversation about stories should not activate the skill.

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 (4)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The README includes a one-liner that directly modifies the user's crontab and creates recurring background execution, but does not clearly warn that it installs persistence. In a skill context, copy-pasteable persistence mechanisms are risky because users may not understand they are enabling automatic execution of code from the skill directory every day.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger keywords include common everyday phrases like '講故事', '睡前故事', and '晚安故事', which are broad enough to be said in normal conversation without intent to invoke the skill. This can cause unintended activation, especially in family or childcare contexts where these phrases are naturally frequent, leading to surprising behavior or workflow hijacking by the skill.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The description says the skill starts whenever parents say '講故事 / 睡前故事 / 床邊故事', which is overly broad and lacks clear activation boundaries. In practice, this increases the chance the agent will activate during ordinary discussion about stories rather than an intentional request, making accidental execution more likely.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The additional trigger list expands activation to generic phrases in multiple languages, including '說故事', '聽故事', 'Story time', and 'Bedtime story', without scope limits. This materially increases accidental activation risk because these are common phrases that may appear in casual speech, translation, or quoted text.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.