ClawHub
Back to skill

Security audit

Plants

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward plant-care note system that creates local plant files, with minor surprise risk from broad activation wording.

Install this if you want a local file-based plant care tracker. Be aware it may create and maintain files under ~/plants/ and store personal plant details such as room locations and photo references; ask the agent to confirm before creating new plant entries if you want tighter control.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger condition is broad enough that ordinary mentions of plants could activate the skill unexpectedly, causing it to take workflow actions the user did not clearly request. In this skill, unintended activation is more concerning because the skill is designed to create and manage persistent files, so an ambiguous trigger can lead to unwanted file creation or modification in the user's environment.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill explicitly creates a workspace under the user's home directory but does not warn the user in the description or behavior that local files will be created there. This reduces informed consent and can surprise users with persistent artifacts, especially if activation happens incidentally through the broad trigger behavior.

Static analysis

No suspicious patterns detected.