ClawHub
Back to skill

Security audit

Gravity Field Empowerment

Security checks for vulnerabilities and agentic risk

Overview

This is a business analysis framework skill with no executable behavior, though its activation wording may make it appear in broad transformation or ROI discussions.

Install this if you want an agent to apply this specific long-term business-intervention measurement framework. Be aware it may activate for fairly general transformation or ROI questions, so users should redirect the agent if they want a different strategy framework.

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
Confidence
86% confidence
Finding
The activation criteria are broad and based on common business-evaluation phrasing, which can cause the skill to trigger in many general strategy or coaching conversations beyond the narrow cases it is meant for. Over-broad activation is a genuine security and safety concern for agent skills because it can inappropriately steer conversations, overshadow better-suited skills, and create unintended autonomous behavior, even though this file contains no direct malicious payload.

Static analysis

No suspicious patterns detected.