Security audit
Security checks for vulnerabilities and agentic risk
This frontend design skill has broad but disclosed file and command permissions, with no evidence of hidden payloads, persistence, or destructive behavior.
Install only if you are comfortable with a frontend assistant that may read and modify project files and run normal development commands. Review generated code, approve commands and external API calls explicitly, and do not provide secrets or sensitive design materials unless needed.
The invocation description is broad and ambiguous, which weakens user understanding of what the skill may actually do. In a skill that also references write, exec, and API behaviors, ambiguity increases the chance of overbroad invocation, unsafe assumptions, and prompt-driven scope creep.
These documented capabilities broaden the skill from a narrow frontend design assistant into a general-purpose automation surface including file handling, API usage, command execution, and information retrieval. That mismatch makes the skill more dangerous because a user may invoke it for benign design work while the agent is authorized and socially primed to perform much riskier actions.
The markdown describes file writing, API integration, and command execution without prominent user-facing warnings about their consequences. That omission is dangerous because it reduces informed consent and makes it easier for a design-themed skill to perform impactful actions on the local system or external services unexpectedly.
The file advertises external API integration even though the skill is framed as a frontend design tool. This broadens the trust boundary to remote services and can enable unintended data exfiltration, dependency on unvetted endpoints, or behavior inconsistent with the expected design-only purpose.
The skill is presented as a frontend design capability, but the documentation also advertises generic command execution. That expands the operational scope far beyond design assistance and can normalize running arbitrary commands under a design-themed skill, increasing the chance of misuse or user surprise.
The security section claims restricted or safe command execution, but the rest of the document presents broad execution capability without any concrete technical enforcement. This can create false confidence for users and reviewers, causing them to trust the skill more than its documented controls justify.
No suspicious patterns detected.
