ClawHub
Back to skill

Security audit

family-hotel

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its travel-search purpose, but it directs automatic local CLI installation and appears to persist raw travel queries in logs without clear user control.

Review before installing. This skill may run local shell commands, globally install a third-party npm package, contact an external travel booking service, and retain local execution logs. Only use it if you trust the flyai CLI and are comfortable sharing and possibly locally logging travel-search details.

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 (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to run `npm i -g @fly-ai/flyai-cli` if the CLI is missing, but it provides no warning, consent step, or trust guidance before installing a global package. Executing package installation commands on the user's machine can alter the environment and introduce supply-chain risk if the package or registry is compromised.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill frames the agent as a 'CLI executor' and mandates command execution without clearly notifying the user that shell commands will be run on the local machine. In an agent setting, this can cause users to unknowingly authorize local command execution, increasing the risk of unintended system changes or abuse through chained prompts.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The runbook explicitly records `user_query` as raw input in an internal execution log, which can capture sensitive personal, travel, identity, payment-adjacent, or visa-related information. In this skill context, users may provide family details, children-related requirements, passport or itinerary data, so retaining raw queries without disclosure, minimization, or retention controls creates a meaningful privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The runbook instructs the agent to append execution logs to a local file, creating persistent storage of potentially sensitive operational data with no notice, consent, encryption, or lifecycle controls. Because this family-travel skill may process booking requests, family composition, locations, dates, and visa/travel details, local log persistence increases the chance of unintended disclosure or later compromise.

Static analysis

No suspicious patterns detected.