The Agent Skills Directory

[SAFE]: The skill defines a professional persona for frontend development without any signs of malicious intent or behavior. All referenced experts and resources are legitimate and industry-standard for the field.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it is instructed to process untrusted data from local files and the web while having access to the Bash tool. * Ingestion points: The skill uses Read, Glob, Grep, and WebFetch tools to analyze local project code and external web content. * Boundary markers: There are no explicitly defined delimiters or instructions to ignore embedded commands within the data being analyzed. * Capability inventory: The skill has access to the Bash tool for command execution and various tools for network and file system access. * Sanitization: No explicit input validation or sanitization of external content is mentioned in the instructions.

frontend-expert