ClawHub
Back to skill

Security audit

Voice Memo

Security checks for vulnerabilities and agentic risk

Overview

The skill’s voice-memo purpose is coherent, but it stores potentially sensitive memo content and schedules reminders without enough clarity about storage, retention, or user control.

Before installing, confirm where voice memos are stored, who can access them, how to delete them, and whether daily threads or nightly reminders require opt-in. Also verify the missing scripts/voice_memo.js implementation before relying on the skill.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs storing transcribed voice memo text, summaries, decisions, and action items, and also describes scheduled reminder behavior, but provides no notice about retention, sensitivity, consent, or where that data is stored. Voice memos often contain personal, confidential, or business-sensitive information, so silent persistence and proactive reminders can expose private data or create unexpected disclosure risks.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The workflow explicitly mandates '2-3文の日本語要約', which forces a specific language for generated output. This is a natural-language policy concern because the file does not indicate user opt-in, language selection, or a justified region-specific constraint.