ClawHub
Back to skill

Security audit

Booking Real Time Hotel Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent hotel-search integration that sends user-provided travel search details to a clearly identified Booking Live API service.

Install this only if you are comfortable sending hotel search details such as destination, dates, guest count, filters, and hotel names to the Booking Live API on RapidAPI. Review the broad triggers if your agent supports editing them, and keep the RapidAPI key scoped to this service where possible.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list is unusually broad for a hotel-search skill and includes generic phrases such as "booking", "accommodation", "stay in", and "hotel near" that can match ordinary conversation outside a clear user request to invoke this tool. That increases the chance of unintended activation, causing unnecessary collection and transmission of travel-related user data to the third-party API and potentially surprising the user.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to send destination, dates, occupancy, and hotel names to a third-party RapidAPI-backed service but does not include a clear user-facing privacy notice or consent mechanism. Users may disclose sensitive itinerary information without realizing it will be transmitted externally, which creates privacy and compliance risk even if the API is legitimate.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This instruction explicitly directs outbound network requests to an external API using a secret-bearing header, meaning user-supplied travel details and the RapidAPI-backed request are transmitted off-platform. In context this is expected functionality, but it is still a real external-transmission risk because the skill also encourages immediate execution and broad triggering, which reduces user awareness and increases chances of unintended data sharing.

Content

Scanner excerpt · SKILL.md (reported line 153)May include surrounding context.

md
### How to Make Requests

**IMPORTANT: Always use `curl -s` to call the API. Do NOT use Python `requests` or any other library that may not be installed.** `curl` is always available and is the preferred method. Always include both RapidAPI headers.

**CRITICAL: Keep it simple.** Run a single `curl -s` command and read the JSON response directly. Do NOT pipe through Python, do NOT write to temp files, do NOT use complex shell pipelines. The JSON response is small enough to read directly from the curl output.

Static analysis

No suspicious patterns detected.