The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the grep utility to scan the codebase for design system structures, components, and hard-coded values.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the analysis of project source code.
Ingestion points: The agent reads local source code files (scripts, components, stylesheets) to identify patterns and tokens.
Boundary markers: No specific delimiters or instructions to ignore embedded prompts in the analyzed data are provided.
Capability inventory: The skill allows the agent to create new components, modify existing code, and delete redundant implementations.
Sanitization: There is no evidence of sanitization or validation of the content read from external source files before it is processed by the model.

extract