Security audit
Security checks for vulnerabilities and agentic risk
This cruise recommendation skill is under-documented and sends requests to a hosted MCP gateway, but the reviewed artifacts do not show hidden execution, persistence, credential access, destructive behavior, or deception.
Install only if you are comfortable sending cruise search terms or preference details to the listed CruiseSkillBridge/Ola Vacations MCP gateway. Avoid sharing sensitive travel history, personal identifiers, or payment/account information until the publisher documents data handling and replaces the placeholder capability text.
The README uses Chinese for the core skill description and installation guidance, but does not indicate that the skill is intended only for Chinese-speaking users or provide any language/locale opt-in. This can violate language/locale policy because it implicitly forces a specific language for all users.
The skill claims to provide personalized cruise recommendations based on user preferences and history, but the documented implementation only describes a generic POST request and a keyword search tool. This mismatch is dangerous because users or downstream agents may disclose sensitive preference/history data under false assumptions about how it will be processed, creating deception and possible inappropriate data handling.
The skill instructs callers to send POST requests and states that requests are forwarded through a gateway with statistics collection, but it does not warn users that their data may be transmitted to third parties and logged. This creates a privacy and transparency issue, especially for a recommendation skill that may collect user preferences or history that could be sensitive.
The visible instructional and descriptive text in this file is entirely Chinese, which can impose a language requirement on users without opt-in. The policy for this category flags language or locale constraints unless the skill offers a choice or clearly documents a justified region-specific limitation.
The description is written entirely in Chinese and presents the skill behavior in that language without any indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking region. Under the policy, language-specific behavior should either be optional for the user or clearly justified.
The user-facing description and instructions are written in Chinese, but the file does not indicate that the skill is China-region-specific or provide an opt-in/alternative language. This can violate language/locale policy when a skill implicitly constrains users to a specific language without notice or choice.
The capability section is left as template placeholder text instead of describing the skill's real inputs, outputs, and constraints. This is risky because security reviewers, users, and calling agents cannot accurately assess what data is needed or what actions the skill will take, increasing the chance of unsafe or over-privileged use.
