ClawHub
Back to skill

Security audit

Edit

Security checks for vulnerabilities and agentic risk

Overview

This is a plain editing-skill prompt that helps revise existing writing and does not request tool, file, network, credential, or persistence access.

Install this if you want a general-purpose editing assistant. Be aware it may activate on ambiguous requests like "make this better," so give clear context when you want drafting, summarization, critique, or another specialized task instead.

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
Confidence
94% confidence
Finding
The trigger phrases are broad enough to match many generic writing-improvement requests, which can cause the skill to activate in situations beyond a narrowly scoped editing task. While this is not an exploit in itself, ambiguous activation can lead to incorrect routing, unintended handling of user content, or interference with more appropriate specialized skills.

Static analysis

No suspicious patterns detected.