ClawHub
Back to skill

Security audit

Goals

Security checks for vulnerabilities and agentic risk

Overview

This is a simple goal-planning skill that stores goal notes locally and does not show hidden code, network access, or deceptive behavior.

Before installing, be aware that the skill may help maintain personal goal notes in ~/goals/. Confirm the folder location before allowing file creation, especially if goals include sensitive personal or financial details.

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
95% confidence
Finding
The skill describes activation in broad natural language such as 'User mentions an aspiration' and 'surface when relevant' without defining clear trigger phrases or exclusion conditions. These phrases overlap with common conversation and make it unclear when the skill should activate versus remain inactive.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs creation of a `~/goals/` workspace without any explicit user consent or warning, which can cause unintended filesystem writes on the host system. Even though the path and purpose are benign, silent file creation violates least surprise and can become risky in environments where agents have broad local access or where users did not intend persistent storage.

Static analysis

No suspicious patterns detected.