ClawHub
Back to skill

Security audit

记忆助手演示

Security checks for vulnerabilities and agentic risk

Overview

This is a simple memory-note helper whose local file creation and searching behavior is disclosed and fits its stated purpose.

Before installing, understand that this skill may guide your agent to create, append, search, and manually edit local memory files. Confirm the target paths and contents before writing, especially if MEMORY.md or the memory directory contains important or private notes.

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 (1)

Missing User Warnings

Low
Confidence
92% confidence
Finding
The skill explicitly instructs writing to local memory files using shell redirection, but it does not warn that this modifies persistent local state or discuss safeguards such as confirming paths, validating filenames, or obtaining user consent. In this context the commands are simple and not obviously malicious, but they can still cause unintended data modification or overwrite/append behavior if used carelessly.

Static analysis

No suspicious patterns detected.