ClawHub
Back to skill

Security audit

Google Flights Realtime API

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real flight-search skill, but it can automatically run broad shell-based API searches using a RapidAPI key, which may expose travel details and consume paid quota without enough user control.

Install only if you are comfortable giving the agent a RapidAPI key and sending origins, destinations, dates, and filters to the RapidAPI-backed flight service. Ask the agent to confirm the number of requests before broad date-range or multi-destination searches, especially if your RapidAPI plan can incur charges.

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
91% confidence
Finding
The skill mandates generating and running shell commands and even multi-request bash scripts for a task that only needs structured HTTPS requests. Expanding the execution surface to shell scripting increases the risk of command injection, unsafe interpolation of user-derived values, and accidental execution of unintended commands if inputs like airport codes, dates, or arrays are not strictly validated.

Vague Triggers

Medium
Confidence
88% confidence
Finding
Several trigger phrases such as 'fly to', 'round trip', or 'cheap flights' are broad enough to activate the skill during ordinary conversation, potentially causing unintended third-party requests. Because the skill performs outbound network calls with user travel details, overbroad activation can lead to privacy leakage and surprising side effects without clear user intent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends user itinerary details to a third-party RapidAPI-backed service but does not clearly disclose that travel query data will leave the host environment. This creates a privacy and transparency issue, especially because travel plans can be sensitive and users may not expect external transmission to a non-first-party provider.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.