The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses terminal tools (run_terminal_command, Shell) to delete the KODA-TODO.md file once all tasks are completed. This is a routine operation for cleanup in this context.
[DATA_EXPOSURE]: The skill reads and writes to a specific local file (KODA-TODO.md) to track progress. It does not access sensitive system files or credentials.
[INDIRECT_PROMPT_INJECTION]: The skill relies on instructions stored in a file it creates and reads. While this technically creates a surface where external data influences the agent, it is the primary intended function of a task manager.
Ingestion points: Reads task instructions from KODA-TODO.md.
Boundary markers: None present; the agent treats the file content as its task list.
Capability inventory: File system access (read/write/edit) and shell command execution.
Sanitization: No specific filtering is applied to the tasks defined in the file.

koda-todo