The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a bundled Python script (.claude/skills/todo/scripts/tasks.py) to perform task operations such as listing, adding, and updating tasks. This execution is scoped to the skill's own logic and manages local workspace data.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data that could be influenced by external actors.
Ingestion points: Data is read from my-data/tasks.jsonl (via the Python script) and markdown files in my-data/daily-plans/.
Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings when the agent reads task titles or daily plan content.
Capability inventory: The skill possesses file-write and file-read capabilities within the my-data directory and executes a local Python script.
Sanitization: No validation or sanitization of task content is performed before the agent processes the data for daily planning.

todo