Back to skill

Security audit

book-hotels

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed hotel-search helper that uses the RollingGo CLI and API key, with some credential-handling documentation issues users should watch.

Before installing, verify that you are comfortable running the RollingGo CLI from npm or PyPI at the latest version and providing it a RollingGo API key. Prefer host-scoped environment injection over command-line --api-key usage, and confirm which exact API key variable name the installed CLI expects.

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 (3)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill declares `primaryEnv` and required env as `RollingGo_API_KEY`, but the operational instructions require `ROLLINGGO_API_KEY`. This inconsistency can cause the agent to believe credentials are missing when they are present, or to use a different variable than the host expects, leading to failed execution and potential accidental disclosure or misconfiguration during troubleshooting.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation explicitly shows passing the API key on the command line (`--api-key YOUR_API_KEY`) without warning that command-line arguments may be exposed via shell history, process listings, CI logs, or telemetry. In an agent or hosted execution environment, this is more dangerous because secrets may be captured by orchestration layers or debugging output outside the user's control.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation explicitly shows 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 telemetry. In a skill that may be executed by agents or hosts with logging and command auditing, this increases the chance of credential disclosure beyond the immediate user session.

Static analysis

No suspicious patterns detected.