ClawHub
Back to skill

Security audit

Dataify Google Hotels

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent hotel-search skill that uses Dataify as disclosed, with normal cautions around third-party travel-query sharing and API-token handling.

Install only if you are comfortable with Dataify receiving the hotel search details you ask it to process and with the skill using a Dataify API token from your environment or command arguments. Prefer a session-scoped environment variable unless you intentionally want persistent shell configuration, and avoid using it for highly sensitive travel plans if third-party API processing is not acceptable.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs the agent to read local reference files, inspect environment variables for `DATAIFY_API_TOKEN`, and make external network requests via a Python script, yet no permissions are declared. This creates a capability/consent mismatch: a reviewer or runtime may underestimate what the skill can access and do, increasing the risk of unintended secret access or unreviewed outbound requests.

Missing User Warnings

Medium
Confidence
78% confidence
Finding
The script sends user-provided travel search data, dates, occupancy, and filters to a third-party API endpoint, but the normal execution path does not present a clear, user-facing disclosure at transmission time. In an agent-skill context, this can cause unintentional external sharing of potentially sensitive itinerary or location data, especially if users assume processing is local.

Missing User Warnings

Medium
Confidence
70% confidence
Finding
The script automatically reads an API token from the environment and also writes the normalized Bearer-form token back into DATAIFY_API_TOKEN without any prominent warning about credential sourcing or persistence behavior. In a shared agent/runtime environment, this can surprise operators and increase the chance of credential exposure through inherited environment state or downstream subprocess behavior.

Static analysis

No suspicious patterns detected.