ClawHub
Back to skill

Security audit

Scavio Booking

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Booking.com hotel-data integration that uses a Scavio API key to make purpose-aligned hotel search, property, and review requests.

Install only if you are comfortable using Scavio as a third-party API provider for hotel research. Set SCAVIO_API_KEY as an environment secret, monitor credit usage, and avoid sending sensitive personal travel details beyond what is needed for the search.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

External Transmission

Medium
Category
Data Exfiltration
Content
STAY = {"checkin": "2026-09-08", "checkout": "2026-09-10", "currency": "USD"}

# 1. Search a destination for a real stay - dates always in pairs
found = requests.post(f"{BASE}/api/v1/booking/search", headers=HEADERS,
    json={"destination": "Austin", "adults": 2, "rooms": 1,
          "sort_by": "review_score", "min_review_score": "8",
          "max_price": 300, **STAY}).json()
Confidence
70% 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
STAY = {"checkin": "2026-09-08", "checkout": "2026-09-10", "currency": "USD"}

# 1. Search a destination for a real stay - dates always in pairs
found = requests.post(f"{BASE}/api/v1/booking/search", headers=HEADERS,
    json={"destination": "Austin", "adults": 2, "rooms": 1,
          "sort_by": "review_score", "min_review_score": "8",
          "max_price": 300, **STAY}).json()
Confidence
70% 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
row = found["data"]["properties"][0]

# 2. Chain the URL the row already gave you - no country_code guessing
hotel = requests.post(f"{BASE}/api/v1/booking/hotel", headers=HEADERS,
    json={"hotel": row["url"], **STAY}).json()

# The response echoes the dates it actually priced
Confidence
70% 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
print(hotel["data"]["checkin"], hotel["data"]["checkout"], hotel["data"]["nights"])

# 3. Guest reviews for the same property
reviews = requests.post(f"{BASE}/api/v1/booking/reviews", headers=HEADERS,
    json={"hotel": row["url"], **STAY}).json()

# 4. A family stay: children_ages are AGES, not a headcount
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:37