ClawHub
Back to skill

Security audit

Project Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed project-management workflow that reads and updates one JSON task file, with clearly described optional reminder sync and chat notification side effects.

Install this only if the hardcoded projects.json path, Apple Reminders sync for sync:true tasks, and David chat notifications match your workflow. Avoid putting secrets or highly confidential details in task titles that may be synced or messaged.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill specifies that tasks may be synchronized to Apple Reminders when `sync: true`, which sends task content to an external application/service without any stated user consent, warning, or data-minimization controls. Project tasks can contain sensitive business information, so silent transmission outside the local JSON store creates a privacy and data-leak risk.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to notify David in chat when tasks move to `review` or `blocked`, which shares internal project status with another party without any warning, authorization check, or scope restriction. Because task titles/statuses may reveal confidential roadmap, operational, or personnel information, this can leak sensitive data through chat channels.

Static analysis

No suspicious patterns detected.