ClawHub
Back to skill

Security audit

Towel Closet Shelf Map

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only towel closet organization skill with no code, network, credential, or persistence behavior.

Installing this skill should only affect how the agent formats practical towel closet organization advice. Users who need another language or regulated hygiene, rental, hotel, daycare, clinical, or infection-control guidance should not rely on this skill for that purpose.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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 (4)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- Short labels ready to copy
   - Optional small sublabels for baskets
5. **Reset Routine**
   - Laundry-day return rule
   - Guest-prep check
   - Monthly overflow check
6. **Restock and Overflow Notes**
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
Line L06 states 'Language is English only,' which is a natural-language locale policy constraint. The file does not offer the user any language choice or explain a justified region-specific need, so this matches the policy-violation category for forced language without opt-in.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The manifest sets `language: "en"`, which is a natural-language locale constraint. The file does not indicate user opt-in, multilingual support, or a region-specific justification for restricting the skill to English.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The manifest sets "language": "en", which indicates a fixed language choice. Under the policy, forcing a specific language without user opt-in or a clear region-specific justification is a natural-language policy concern.

Static analysis

No suspicious patterns detected.