The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files which could be manipulated to influence agent behavior.
Ingestion points: The agent is instructed to read components.json and project structures using Read, Glob, and Grep tools to identify existing styles and configurations.
Boundary markers: The instructions lack explicit delimiters or warnings to treat the content of components.json or other codebase files as untrusted data.
Capability inventory: The skill has access to the Bash, Write, and Edit tools, enabling it to execute commands and modify the filesystem based on the processed data.
Sanitization: There is no evidence of validation or escaping for project-derived values (such as aliases or style names) before they are interpolated into CLI commands.
[COMMAND_EXECUTION]: The skill mandates the execution of shell commands via package manager runners (e.g., npx, bunx, pnpm dlx) to initialize the library and add components. These commands rely on parameters extracted from the local environment.

shadcn-registries