ClawHub
Back to skill

Security audit

home-memory

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent but needs review because it sends household context to an external persistent memory service and directs broad post-interaction storage without clear consent or limits.

Install only if you are comfortable sending selected household notes to BlueColumn for persistent storage. Avoid storing addresses, access codes, landlord contact details, schedules, financial or health information, and ask the agent to confirm exactly what will be saved before it calls the memory API.

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
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly routes household context to an external persistent memory service, but the description and usage guidance do not clearly warn the user that potentially sensitive home-related data will leave the local agent context and be stored remotely. This creates a meaningful privacy and consent risk because users may share addresses, landlord details, schedules, maintenance notes, or other household information without realizing it is being transmitted to and retained by a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This example demonstrates outbound transmission of household context to a third-party API, including potentially sensitive information such as landlord contact details and maintenance records. While external transmission is core to the skill's purpose, it is still security-relevant because it moves user data outside the agent boundary and into a persistent service, where confidentiality and data handling depend on the external provider.

Content

Scanner excerpt · SKILL.md (reported line 15)May include surrounding context.

Store

bash
curl -X POST .../agent-remember \
  -H "Authorization: Bearer <key>" \
  -H "Content-Type: application/json" \
  -d '{"text": "HVAC filter due Aug 15. Landlord email on file.", "title": "home-memory - note"}'

Ssd 3

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The workflow directs the agent to store a summary after every interaction, which encourages broad, automatic retention of conversation-derived data in natural language form. That can capture sensitive household details, personal contacts, routines, access information, or other unintended data, increasing exposure in the event of misuse, overcollection, or compromise of the external memory service.

Content

No source excerpt is available for this finding.