ClawHub
Back to skill

Security audit

MyMacOptimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently lets an agent operate a local Mac optimizer app, including monitoring, scans, and user-confirmed cleanup or deletion actions.

Install only if you trust the local My Mac Optimizer app that provides the 127.0.0.1:8000 API. Treat cleanup, uninstall, and file-delete actions as high impact, and confirm exactly what will be removed before allowing those commands to run.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Content
### 1. System Health & Monitoring
Check the current state of the Mac (CPU, RAM, network, etc.).
```bash
curl http://127.0.0.1:8000/api/performance
curl http://127.0.0.1:8000/api/system
```
Confidence
88% confidence
Finding
The skill instructs an agent to send HTTP requests to a local service that exposes sensitive system state such as CPU, RAM, and network information. Even though the destination is localhost rather than an external host, this still expands the agent's ability to access and act on privileged local resources through an unauthenticated local API, which can enable unauthorized system inspection and follow-on destructive actions when combined with other endpoints in the skill.

Static analysis

No suspicious patterns detected.