ClawHub
Back to skill

Security audit

MVP

Security checks for vulnerabilities and agentic risk

Overview

This is a mostly ordinary MVP guidance skill, but it includes under-disclosed validation advice that can encourage misleading real users.

Review this skill before use if you plan to follow its validation playbooks with real users. Prefer transparent wording such as pilot, beta, manually assisted, coming soon, or refundable pre-order, and avoid using these tactics where users could be harmed by hidden manual handling, unclear availability, or ambiguous payment terms.

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 'Wizard of Oz' section explicitly states that the user thinks the service is automated while the work is performed manually, which endorses deceptive behavior without any guardrails, disclosure guidance, or ethical limitations. In a product-launch skill, this can normalize misleading users about how a product operates, creating trust, reputational, legal, and compliance risks if operators collect data, payments, or sensitive information under false pretenses.

Static analysis

No suspicious patterns detected.