ClawHub
Back to skill

Security audit

Design Hotel

Security checks across malware telemetry and agentic risk

Overview

This hotel-search skill is mostly coherent, but it quietly keeps raw travel-query logs and can broaden budget, date, and lodging constraints without user confirmation.

Review before installing. Use it in a controlled environment, verify the @fly-ai/flyai-cli package, avoid entering passport, payment, or other sensitive personal details, and delete or disable .flyai-execution-log.json if you do not want local travel-query history retained. Confirm any budget, date, location, or lodging-type changes before acting on booking links.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The fallback logic explicitly expands searches city-wide, relaxes budget limits by 30%, shifts travel dates, and drops user-provided filters without requiring warning or consent. In a travel-booking context, this can cause the agent to return or act on options that materially violate user intent, leading to financial harm, booking mistakes, or misleading recommendations.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The fallback hard-codes the hotel type value "民宿" rather than deriving it from the user's language or stated preference. This can skew results toward a specific lodging category the user did not request, reducing result integrity and potentially causing unsuitable bookings in a commerce workflow.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The runbook explicitly logs raw user input, CLI commands, timestamps, and execution details in an internal schema without any stated minimization, redaction, consent, or retention controls. In a travel-booking skill, user queries can contain sensitive personal and trip information, so persistent collection of this data increases privacy and disclosure risk if logs are accessed, exfiltrated, or reused beyond the original request.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The runbook instructs the agent to append execution logs to a local file, creating persistent storage of potentially sensitive operational and user-derived data without any warning or safeguards. Local log files are often broadly readable within a runtime, accidentally bundled, or exposed through support/debug workflows, making this a practical data leakage risk rather than a purely theoretical concern.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.