The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of the okou CLI tool and its various subcommands (generate, host, doctor) to perform its primary functions. These operations are within the scope of the skill's intended use-case.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input and interpolates it directly into command-line arguments such as --prompt and --script.
Ingestion points: User-provided descriptions and scripts processed in SKILL.md.
Boundary markers: The instructions do not define delimiters or specific "ignore embedded instructions" warnings for the user-supplied content.
Capability inventory: The skill possesses the ability to execute shell commands and write/host files on the local system.
Sanitization: While the skill suggests using temporary files for long prompts to avoid shell quoting issues, it does not mandate specific sanitization or filtering of the content to prevent malicious instruction injection.
[DYNAMIC_EXECUTION]: The skill facilitates the creation and hosting of dynamic HTML artifacts (e.g., websites, presentations). The agent authors these artifacts based on output received from the CLI and then makes them available via the okou host command, representing the intended dynamic generation workflow.