ClawHub
Back to skill

Security audit

Mit24 Value Proposition

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown business-planning skill with no code execution or hidden privileges, though users should handle prospect contact details carefully.

Install is reasonable for business-planning use. When using the prospect-list step, keep entries limited to necessary business outreach details, use consent-based or lawfully sourced contacts, and redact personal identifiers when a profile or role description is enough.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs users to produce a list of 10 potential customers' contact information, which encourages collection and sharing of personally identifiable or business contact data without any privacy guardrails, consent requirements, or minimization guidance. In a business-planning skill, this makes unauthorized scraping, inappropriate storage, or oversharing of personal data more likely, especially if users paste real names, emails, phone numbers, or employer details into the assistant.

Static analysis

No suspicious patterns detected.