ClawHub

Aerobase Travel Pro

Security checks across malware telemetry and agentic risk

Overview

The skill mostly fits its travel-planning purpose, but it tells the agent to repeatedly check and proactively report travel deals without clear opt-in or controls.

Review before installing if you do not want an agent making recurring Aerobase requests with your API key. Use a dedicated key if possible, monitor quota, avoid sending sensitive itineraries or meeting details unless you trust Aerobase, and only allow deal monitoring after an explicit user decision.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs periodic monitoring and proactive surfacing of travel deals, which is behavior beyond on-demand jetlag analysis. This creates an unsolicited data-processing and outreach path that can trigger external calls and user-facing recommendations without a contemporaneous user request, increasing privacy, consent, and scope-creep risk.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The instruction to run 'every few hours or at the start of each session' is an overly broad trigger that can cause unintended automatic invocation. In an agent environment, this can lead to repeated external API calls, unprompted behavior, and actions taken outside the user's immediate intent.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill description and monitoring section do not provide a clear warning that the agent may periodically check external services and proactively message users about deals. Lack of upfront disclosure undermines informed consent and can surprise users with monitoring behavior they did not expect from a jetlag-planning skill.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal