ClawHub
Back to skill

Security audit

Willow Memory Health

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed memory-audit helper that reads a user-selected memory folder and reports cleanup candidates, with changes gated on user confirmation.

Before installing, understand that this skill can inspect markdown files in the memory folder you point it at. Review the exact files before approving any archive, merge, qmd update, or memory-summary write.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill instructs the agent to read arbitrary memory directories and execute shell commands (`python3 ...`, optionally `qmd update`) but does not declare corresponding permissions. That mismatch is a real security issue because it hides the skill's operational capabilities from permission review and could lead to unexpected filesystem access or command execution when the skill is invoked.

Static analysis

No suspicious patterns detected.