ClawHub
Back to skill

Security audit

Hospitality

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent hotel-operations playbook, but it normalizes handling guest personal data and outbound messaging without clear privacy, consent, or integration safeguards.

Review before installing in a real property workflow. Use only approved hotel systems, collect the minimum guest data needed, avoid exposing payment or identity details in messages, check consent for marketing or review outreach, and require secure handling of API credentials and webhooks.

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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly directs collection and logging of guest names, contact details, booking references, payment status, special requests, loyalty data, and operational notes, but provides no privacy boundaries, data minimization guidance, retention limits, or access controls. In a hospitality context this is sensitive customer data, so normalizing broad storage and internal sharing without safeguards creates real risk of over-collection, unauthorized disclosure, and noncompliant handling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs outbound guest messaging across pre-arrival, during-stay, post-checkout, and review workflows using customer stay details, but does not warn that these communications may expose personal data through email, chat, OTA platforms, or other third-party channels. This is dangerous because staff or agents may send unnecessary booking or identity details over insecure or unapproved channels, increasing privacy, phishing, and compliance risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill recommends monitoring review platforms and potentially using API or webhook integrations, but does not mention third-party data sharing, credential handling, or limits on what guest information should be pulled, stored, or forwarded. The direct impact is lower than the reservation and messaging sections, but it still creates a real risk of overbroad external access, accidental data aggregation, and insecure integration practices.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.