Security audit
Security checks for vulnerabilities and agentic risk
This is mainly a frontend design/code-generation skill, but it asks for command execution and unspecified API access without tight limits.
Review before installing. Use it only in a sandbox or workspace you are comfortable modifying, and require confirmation before it runs commands, writes files, or sends content to any external API. Do not provide secrets unless the exact service and data use are clear.
The activation scope is overly broad, covering many types of design and code-generation requests without clear boundaries. Over-broad triggers increase the likelihood that the agent will invoke the skill in contexts the user did not intend, which is especially risky when the skill also has read/write/exec capabilities.
The trigger phrases mix frontend page design with broader creative domains such as poster/brand visual work, which blurs the skill’s intended role. This ambiguity can cause accidental invocation on unrelated requests and thereby expose unnecessary tool permissions in contexts where they are not needed.
The description states '支持中文交互，无需复杂配置即开即用', presenting Chinese interaction as the expected mode without offering a user choice of language. This is a natural-language locale policy issue because it defaults to a specific language rather than clearly making it optional.
The markdown does not clearly warn users that the skill may read files, write files, and execute commands. In a tool-enabled agent, lack of transparent disclosure undermines informed consent and can lead users to invoke a seemingly harmless design skill that actually has materially more powerful local capabilities.
The markdown highlights '本技能提供中文交互' in the core functionality section, but does not indicate that users may choose another language. This can be read as forcing a locale preference, which violates the policy unless the choice is optional or justified.
The skill advertises API/external service integration despite being described primarily as a frontend design/code-generation skill, and the documentation does not clearly explain why network access is needed or what data may be sent externally. This ambiguity can lead to unintended exfiltration of user content, project files, or secrets if the agent uses external APIs during operation.
The skill is presented as a frontend UI/code-generation tool, but it also declares command execution capability without a narrowly scoped, purpose-bound justification. In an agent environment, adding exec to a design skill materially expands the attack surface and can enable arbitrary local command execution if future prompts or templates route user-controlled content into shell commands.
The file mixes a generic structured processing API contract with a frontend design skill description, creating contradictory intent signals about what the skill actually does. Ambiguous interfaces make it easier for an agent or user to invoke the skill in unintended ways, which increases the chance of unsafe tool use or mishandling of untrusted input.
No suspicious patterns detected.
