ClawHub
Back to skill

Security audit

记忆编排器免费版

Security checks across malware telemetry and agentic risk

Overview

This is a simple memory-management skill whose local storage behavior is disclosed and aligned with its purpose, with privacy caveats users should understand.

Install only if you are comfortable with the agent storing memory contents in local files. Avoid saving secrets, credentials, or highly sensitive personal data, choose a private storage path, and do not use callback URLs unless you fully trust the destination.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 supports saving memory data to local disk, but it does not warn that user content, preferences, or conversation-derived data may contain sensitive information and remain unencrypted on the filesystem. In an agent context, persistent memory often includes personal or confidential data, so silent local storage increases the risk of unintended retention, disclosure to other local users/processes, and insecure backup or sync exposure.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documented callback_url parameter allows results to be sent to an external endpoint, but the skill provides no warning about outbound data transfer, trust boundaries, or validation requirements. In a memory-management skill, callbacks could transmit conversation-derived data or summaries to attacker-controlled infrastructure, creating a straightforward exfiltration path if misused or socially engineered.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.