The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a Java-based server binary (codestyle-server.jar) that is downloaded during initialization. This binary is executed via the scripts/codestyle and scripts/codestyle.bat wrapper scripts to handle template search and retrieval tasks.
[EXTERNAL_DOWNLOADS]: The skill performs several external network operations, including downloading the CLI server binary from GitHub and cloning a template repository from the author's GitHub account. It also utilizes curl and git to fetch data from user-specified URLs and repositories during the code generation workflow.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated code generation workflow that processes untrusted data from external sources.
Ingestion points: Data enters the agent's context through web crawling via curl and cloning external GitHub repositories as described in the generation workflow (references/generate-workflow.md).
Boundary markers: The documentation does not indicate the use of delimiters or instructions to ignore potential commands embedded within the external content during processing.
Capability inventory: The skill is capable of executing CLI commands through its JAR-based server and performing network requests to external APIs for template management.
Sanitization: There is no evidence of input validation or content sanitization for the external data before it is passed to the AI for template analysis and generation.

codestyle