The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the checklist CLI and standard shell commands (such as cat, echo, and which) to manage data and verify configuration settings within the user's environment.
[CREDENTIALS_UNSAFE]: The agent is instructed to access the CHECKLIST_ADMIN_TOKEN environment variable and the ~/.checklist-ledger.json file. These contain authentication credentials required for the task ledger's API operations, which are consequently exposed to the agent's context during verification steps.
[PROMPT_INJECTION]: The skill operates on data fetched from an external API, creating a surface for indirect prompt injection.
Ingestion points: Data is ingested via checklist list, checklist find, and checklist details commands as described in SKILL.md.
Boundary markers: There are no explicit markers or instructions used to distinguish between task content and potential embedded instructions.
Capability inventory: The skill has the ability to execute shell commands and read local files.
Sanitization: There is no mention of sanitizing or filtering the task titles or details retrieved from the remote API.

checklist-ledger