ClawHub
Back to skill

Security audit

Home Server

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed home-server planning and operations helper that keeps local notes only after user confirmation.

Before installing, be aware that this skill is designed to keep persistent local notes about your home-server environment in ~/home-server/. Approve that storage only if you want reusable context saved, avoid putting secrets in the notes, and choose narrow activation preferences if you do not want it to engage on general Docker or networking conversations.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Use natural language observations, not exposed config keys.
- Update `last` whenever home server context changes.
- Promote recurring incidents into explicit prevention notes.
- Never delete prior context without confirmation.
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill instructs activation on very broad, common topics such as Docker, home networking, and reverse proxy usage, which can cause the skill to trigger in conversations beyond the user's intended scope. This increases the chance of unsolicited persistence, context capture, or security guidance being applied in unrelated discussions, creating privacy and control concerns even if the author likely intended convenience.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The template explicitly instructs the agent to create and maintain a file in the user's home directory, which is a local state-changing action. Even though the content is benign documentation, directing file creation and later updates without an explicit consent/checkpoint increases the risk of unintended modification of user data or silent persistence.

Static analysis

No suspicious patterns detected.