Security audit
Security checks for vulnerabilities and agentic risk
This frontend design skill is not clearly malicious, but its instructions expand into unrelated API, file-processing, environment-management, and data-pipeline work while requesting read, write, and exec tools.
Review this skill before installing. It may be reasonable for frontend generation in a controlled workspace, but do not let it perform API integration, environment management, batch file processing, or ETL tasks unless you explicitly intend that and can supervise file writes and command execution.
The file claims the skill only generates frontend interface code, but later advertises API integration, file batch processing, environment management, and data-pipeline usage. In a skill with read/exec/write tools, this scope expansion is dangerous because it normalizes using powerful capabilities outside the stated boundary, making over-privileged execution more likely.
The invocation language is broad enough to match generic design, branding, or creative requests without clear trigger conditions. Over-broad matching can cause the skill to activate in contexts where its exec/write-enabled toolset is unnecessary, exposing users to unintended file modification or command use under a vague design pretext.
The description states '支持中文交互' as part of the skill behavior, and the overall document is written to assume Chinese usage without mentioning multilingual support or user choice. This can violate language or locale policy when a skill appears to force or default to a specific language without explicit opt-in.
The feature note lists '中文交互' as a core capability, but it does not clarify that other languages are supported or that Chinese is user-selectable. Presenting a fixed language expectation can be a natural-language policy issue when no locale choice is provided.
The skill states it does not perform backend/API work, yet later documents callback URLs, API key setup, exec support, and integration-style behaviors. This inconsistency can cause an agent or user to grant broader capabilities than expected, increasing the chance of unintended network access or command execution in a skill that is supposed to be limited to frontend code generation.
The usage scenarios extend into interface integration, content generation, file batch processing, environment management, information retrieval, and ETL-style pipelines, far beyond frontend design. This breadth increases the chance that the skill is selected for high-risk operational tasks where its documented safety model and purpose do not apply.
No suspicious patterns detected.
