ClawHub
Back to skill

Security audit

Memory Four Types

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only memory organization skill, but users should deliberately control what personal or project context gets saved across sessions.

Install only if you want your agent to keep local memories across sessions. Review and prune MEMORY.md, USER.md, SOUL.md, and memory/ files, avoid saving secrets or sensitive personal details, and be cautious before enabling heartbeat, cron, or sub-agent maintenance.

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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill directs the agent to persist user preferences, profile details, and project context into long-lived memory files, but it does not require clear user notice or consent before storing conversation-derived personal data. This creates a privacy risk because users may reveal sensitive background or behavioral information during normal conversation without understanding it will be retained across sessions.

Ssd 3

Medium
Confidence
95% confidence
Finding
The instruction to write ordinary or 'interesting' daily conversation content into daily logs encourages broad retention of natural-language interactions that may contain sensitive personal, business, or security-relevant details. Because the retention rule is content-driven rather than necessity-driven, it increases the chance of over-collection and later leakage through indexing, retrieval, or shared workspace access.

Ssd 3

Medium
Confidence
93% confidence
Finding
Automatically loading today's and yesterday's daily logs at session startup expands access to previously captured conversation data whether or not it is needed for the current task. This increases exposure of retained user content and can surface stale or sensitive information to later sessions, agents, or operators without fresh user intent.

Static analysis

No suspicious patterns detected.