Security audit

find-hotel

Security checks across malware telemetry and agentic risk

Overview

This is a coherent hotel-search wrapper, but users should handle the API key carefully and understand that hotel search details are sent to RollingGo.

Before installing, confirm you are comfortable sending hotel search details to RollingGo. Configure the key via a protected environment variable or secret manager rather than passing it with --api-key, and be aware the docs inconsistently mention ROLLINGGO_API_KEY and RollingGo_API_KEY; the latter is what the metadata and references use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The skill metadata declares `RollingGo_API_KEY` as the primary environment variable, but the pre-flight instructions require `ROLLINGGO_API_KEY`. This inconsistency can cause the agent to incorrectly conclude that credentials are missing or to bypass the intended guardrail logic, leading to failed execution or unsafe fallback behavior. In a security-sensitive tool wrapper, contradictory auth instructions are a real integrity issue because they undermine predictable credential handling.

Intent-Code Divergence

Medium

Confidence: 93% confidence
Finding: The documented API key resolution order includes `RollingGo_API_KEY`, while the mandatory pre-flight section elsewhere requires `ROLLINGGO_API_KEY`. Conflicting credential resolution rules create ambiguity about which secret source is authoritative, increasing the chance of misconfiguration, accidental credential non-use, or inconsistent runtime behavior across hosts and agents.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill sends user-provided travel queries, destinations, dates, occupancy, and hotel preferences to an external service, but the skill description and pre-flight flow do not clearly warn users that their itinerary data will leave the local environment. This is a privacy and transparency issue: users may disclose sensitive travel plans without informed consent, especially because the skill is framed as a simple hotel lookup assistant.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The documentation explicitly recommends passing the API key via the `--api-key` command-line flag and shows concrete examples using the secret inline. Command-line arguments are commonly exposed through shell history, process listings, job control logs, and CI/CD telemetry, so this guidance can lead to credential leakage even if the underlying tool functions correctly.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The documentation explicitly recommends passing the API key via the `--api-key` command-line argument without warning that command-line arguments may be exposed through shell history, process listings, logs, or host telemetry. In this skill context, that is more dangerous because the skill is meant to be executed by agents and users across varied host environments, increasing the chance that secrets are captured by orchestration layers or debugging tools.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.