ClawHub
Back to skill

Security audit

Help Center

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local planning helper for help-center projects and its file storage, memory use, and approval boundaries are disclosed and proportionate.

Before installing, understand that the skill may create and update planning notes under ~/help-center/ if you approve. Choose explicit activation during setup if you do not want it to engage automatically when help-center topics come up.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Content
integration: pending

## Context
<!-- Company support model, audience, channel mix, and constraints -->

## Current Stack
<!-- Existing provider/tools and key integration dependencies -->
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The activation condition is broad enough to trigger on ordinary discussion of help centers, support documentation, or ticket deflection, which can cause the skill to engage without a clear user request. This increases the chance of unintended data collection, memory writes, or workflow steering in contexts where the user only wanted general conversation, especially because the skill also asks to persist preferences in local memory.

Static analysis

No suspicious patterns detected.