ClawHub
Back to skill

Security audit

Cruise Planning Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to use external requests for its stated travel/API function, with no malware or hidden persistence signals, but users should know their request details may leave the local agent.

Before installing, assume trip details or prompts used in requests may be sent to an external service or gateway. Avoid including passports, payment details, or unnecessary personal information unless the endpoint and data handling are clear.

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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users or the hosting agent to send POST requests to an external endpoint and notes that traffic will later be routed through a gateway, but it provides no disclosure, consent, or data-handling constraints. In an agent setting, this can result in sensitive itinerary details, personal information, or user prompts being transmitted off-platform to third parties without clear warning or minimization.

Static analysis

No suspicious patterns detected.