ClawHub
Back to skill

Security audit

airbnb-listing-details-scraper-api-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Airbnb listing scraper that calls BrowserAct with user-provided listing parameters and does not show hidden persistence, local data access, or destructive behavior.

Install only if you intend to use BrowserAct for Airbnb listing extraction and are comfortable sending the requested listing URL or ID, dates, guest count, currency, and your BrowserAct API authorization to BrowserAct. Treat the broad research and lead-generation examples as overbroad marketing language and invoke the skill only for Airbnb listing-detail tasks.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill requires environment access to read `BROWSERACT_API_KEY` and performs networked API calls, but it does not declare an explicit tool scope such as `permissions` or `allowed-tools`. This weakens least-privilege controls and can let a broadly-invoked skill operate with more capability than reviewers or orchestrators can easily constrain.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The description uses broad invocation language like market research, monitoring public records, dataset enrichment, and automation, which overlaps with many common agent tasks. This increases the likelihood of over-selection, where the agent invokes a networked scraping skill in situations only loosely related to the user’s request, expanding data exposure and operational risk.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The listed use cases extend beyond narrowly scraping Airbnb listing details into generic research, lead generation, pricing checks, trend discovery, and broader API automation. This scope inflation can cause agents to apply the skill in contexts the underlying template was not reviewed for, increasing the chance of inappropriate data collection or policy-bypassing automation.

External Transmission

Medium
Category
Data Exfiltration
Content
# API Configuration
TEMPLATE_ID = '113873344637482407'
API_BASE_URL = "https://api.browseract.com/v3/bots"
API_KEY_URL = 'https://www.browseract.com/reception/integrations?co-from=airbnb-listing-details-scraper'
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
# 1. Start Task
    print("Start Task", flush=True)
    try:
        res = requests.post(
            f"{API_BASE_URL}/templates/{TEMPLATE_ID}/runs",
            json=payload, headers=headers, timeout=30
        ).json()
Confidence
80% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.