The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the radar command-line tool (radar map, radar check) to prepare the repository. It includes safety checks to ensure the tool is available before proceeding and explicitly prohibits the agent from attempting to install dependencies itself.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from the local file system, which constitutes a potential attack surface if repository files contain malicious instructions.
Ingestion points: The radar map and radar check commands scan the files within the current repository.
Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions embedded in the analyzed code or the tool's output.
Capability inventory: The skill leverages the agent's ability to execute shell commands and read file system contents.
Sanitization: The skill does not specify any sanitization or filtering of the output from radar check before it is reported to the user.

radar-bootstrap