ClawHub
Back to skill

Security audit

Wardrobe

Security checks for vulnerabilities and agentic risk

Overview

This wardrobe skill is a simple local-file organizer with minor privacy and consent considerations, but no evidence of hidden or malicious behavior.

Before installing, expect the agent to help create a local ~/wardrobe/ folder and store wardrobe notes and photos there; approve the folder location and avoid adding purchase, donation, or photo details you do not want kept in local files.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 120)May include surrounding context.

md
- Cataloging every sock and underwear — focus on visible items
- Rigid capsule rules — personal style matters
- Expensive wardrobe apps — files and photos work
- Guilt about clothing — awareness without judgment

## Maintenance
- Review seasonally: what needs repair or replacement?

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to activate on ordinary clothing-related conversation, which can cause the skill to engage without clear user intent. This is primarily a safety and UX issue: unintended activation may lead to unsolicited advice or file-related setup behavior in contexts where the user did not ask for wardrobe management.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill instructs creation of a workspace directory in the user's home folder without stating that this requires explicit user consent. Any automatic filesystem modification without confirmation violates least surprise and can become more concerning if the skill is triggered accidentally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.