ClawHub
Back to skill

Security audit

Airbnb Listing Detail

Security checks across malware telemetry and agentic risk

Overview

This skill is a purpose-aligned Airbnb listing scraper, but users should know it calls Airbnb's internal API from the browser rather than only reading the current page.

Install only if you are comfortable with an agent making Airbnb API requests from a browser context to collect listing data. Use numeric listing IDs, avoid rapid bulk runs, and do not assume the skill is limited to what is visibly rendered on the current Airbnb page.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill documents active network access to Airbnb's internal GraphQL API via browser-side fetch and scripted execution, yet no corresponding permission declaration is present. This creates a transparency and policy-enforcement gap: reviewers or runtime controls may treat the skill as lower risk than it actually is, allowing outbound requests and scraping behavior without explicit approval.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The operational-boundary statement says the skill only reads data already displayed to the user and never bypasses access controls, but the implementation performs direct GraphQL requests that can retrieve richer backend data independent of the current page state. This misleading documentation can cause operators to authorize the skill under false assumptions, increasing the risk of unreviewed data collection and policy violations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.