Back to skill

Security audit

daily review manager

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed daily review and journaling helper that stores user-provided reflections locally, with privacy considerations but no evidence of hidden or malicious behavior.

Install only if you are comfortable having reflections, transcriptions, moods, and summaries saved in a workspace Markdown file. Use explicit prompts when recording sensitive material, review generated transcriptions, and enable message-platform access or scheduled reminders only when you understand how to turn them off.

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
90% confidence
Finding
The trigger phrases are broad everyday terms such as '周报', '月报', and '今日总结', which can appear in normal conversation without intent to invoke the skill. Because the skill can persist content and process voice/text automatically, accidental activation can lead to unintended capture, transcription, and storage of personal or sensitive information.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The keyword-based intake logic is ambiguous and treats common phrases like '帮我记录' or '今日总结' as sufficient evidence that a message is a review entry. In this skill's context, that is dangerous because the workflow proceeds to transform and store content in Markdown, so ordinary messages may be misclassified and permanently recorded.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.