The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files, including source code and configuration files such as .21st/design.json. This data is used to inform the agent's review and the execution of the 21st CLI tool.
Ingestion points: The skill reads project instructions, design configuration, and relevant source code (SKILL.md).
Boundary markers: No specific delimiters or instructions are present to ensure the agent ignores potentially malicious instructions embedded within the source files.
Capability inventory: The agent can execute the 21st review CLI command with various flags, including --fix, which modifies local files (SKILL.md).
Sanitization: The skill lacks explicit sanitization or validation steps for the content of the ingested files before they are processed by the agent or passed to the CLI tool.
[COMMAND_EXECUTION]: The skill executes the 21st CLI tool, which is a vendor-specific utility from the skill's author. It uses this tool to audit code and apply automated fixes. The execution is driven by the path and content of the project being reviewed.

21st-ui-review