ClawHub
Back to skill

Security audit

Local Business Pack

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is coherent for local-business messaging and reports, but healthcare users should apply privacy and consent checks before using patient outreach templates.

Before installing, healthcare and dental users should review the outreach templates for privacy, consent, and messaging-law compliance, avoid putting sensitive treatment details in SMS, and use approved patient communication channels. For non-healthcare local businesses, the behavior is ordinary drafting and public-research assistance.

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The dental/medical templates encourage sending health-related follow-up messages and appointment prompts using identifiable personal data and references to care or services, but provide no guardrails about patient consent, privacy, or regulated healthcare messaging requirements. In a healthcare context, even seemingly routine outreach can create compliance and confidentiality risk if sent over insecure channels or without proper authorization.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The dental/medical templates explicitly reference prior services and include health-context prompts, which can encourage use of protected or sensitive patient information in outbound messages. In a local-business automation skill, this is risky because users may send PHI-bearing reactivation texts or emails without consent checks, minimum-necessary limits, or compliance guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.