ClawHub
Back to skill

Security audit

Goal Decomposer

Security checks for vulnerabilities and agentic risk

Overview

This is a planning helper that only provides conversational sprint-planning guidance, with no executable code or hidden system access.

Reasonable to install for goal planning and accountability templates. Users should avoid treating it as mental-health, legal, financial, or career-crisis advice, and should review any drafted accountability email before sending personal details to others.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description contains very broad activation cues such as users feeling 'stuck,' 'scattered,' 'unproductive,' or 'unsure what to do next,' which can cause the skill to trigger for many general self-improvement or life-advice conversations outside a narrowly bounded goal-decomposition use case. Overbroad routing increases the chance that this skill is invoked when a more appropriate specialized or safety-reviewed skill should handle the request, leading to mis-scoping, privacy overreach in eliciting personal details, or poor guidance in sensitive contexts like unemployment, mental health-adjacent distress, or major life decisions.

Content

No source excerpt is available for this finding.