Back to skill

Security audit

Cruise Products for Beach Vacations

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a remote cruise-product lookup skill, but its documentation is incomplete and users should avoid sending sensitive personal details.

Review the remote MCP endpoint before use and only send information needed for cruise searches, such as destination, dates, budget, or trip preferences. Do not include passwords, payment details, passport numbers, or other sensitive personal data. The package looks low risk, but its publisher should replace the scaffold text and add a clear privacy/data-handling notice.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (6)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest and title position this skill as exploring cruise products for beach vacations, but the usage section instructs users to submit a generic 'analysis request' with only 'input' and 'skill' fields to httpbin.org/post. This is not merely incomplete documentation; it actively describes a different interaction pattern than a cruise-product exploration tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs users or agents to send POST requests to an external endpoint/gateway without disclosing data handling, sensitivity constraints, or consent expectations. In an agent ecosystem, this can cause prompts, itinerary preferences, identifiers, or other user-supplied data to be transmitted to third-party infrastructure unexpectedly, creating privacy and data-governance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README presents installation and publishing information in Chinese while the rest of the description is in English, with no indication that language selection is optional. This can violate a language/locale policy requiring user choice or explicit justification for a locale-specific presentation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

Most operational instructions and descriptive sections are written in Chinese, while the title and front-matter description are in English. There is no indication that the skill is region-specific or that users can choose their preferred language, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill advertises a specific purpose in the manifest, but the capabilities section says only to 'describe what this skill can do' and 'list key inputs and outputs,' indicating the documentation was not updated for this skill. Because it presents template instructions instead of actual capabilities, it conflicts with the claim that this is a defined, publishable beach-cruise skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file contains key usage instructions in Chinese while other descriptive content is in English, but it does not state any language preference, alternatives, or opt-in. This can violate a language/locale policy when users are implicitly forced into a specific language for installation or configuration steps.

Content

No source excerpt is available for this finding.