ClawHub
Back to skill

Security audit

file-archive-system

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local personal-memory filing skill with privacy considerations, but no hidden code, persistence, exfiltration, or automatic privileged behavior was found.

Before installing, decide whether you are comfortable storing personal memory data in local files. Keep personal-ai-memory private, avoid public repositories or shared sync folders, review any scripts/personal_ai_memory.py file before running the suggested commands, and use encryption or restricted sharing for synced copies.

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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is explicitly designed to store highly personal data such as habits, preferences, schedules, and long-term knowledge, then recommends synchronizing that directory across tools like Git, iCloud Drive, or Syncthing. Although it briefly says not to expose the whole workspace publicly, it does not clearly warn that the memory contents themselves are privacy-sensitive, nor does it recommend encryption, access controls, or avoiding remote/public repositories; this can lead to unintended disclosure of sensitive personal information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The natural-language description and instructions are presented in Chinese, which can impose a language preference on users without opt-in. The file does not indicate that the skill is region-specific or provide an alternative language option.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.