The Agent Skills Directory

[COMMAND_EXECUTION]: The skill operates by executing the tuxedo CLI tool. It uses various subcommands like add, ls, do, and del to manipulate the todo list. Instructions explicitly tell the agent to use the --json and -f flags to automate these interactions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files, which creates a surface for indirect prompt injection.
Ingestion points: The agent reads task data from todo.txt, done.txt, and inbox.txt using the tuxedo ls command.
Boundary markers: There are no defined delimiters or instructions to ignore potential commands embedded within the task text, meaning the agent might interpret task content as instructions.
Capability inventory: Through the tuxedo CLI, the agent can append to files, delete lines, and archive data. It also interacts with the ~/.config/tuxedo/config.toml file indirectly through the tool's behavior.
Sanitization: The skill does not implement sanitization or validation logic for the strings retrieved from the todo files before they are processed.

do-todo-txt