The Agent Skills Directory

[PERSISTENCE]: The skill's primary function is to configure system-level schedulers, including cron jobs, launchd agents, and systemd timers, to ensure the agent's tasks continue to run across sessions.
[DYNAMIC_EXECUTION]: The skill provides instructions for generating and executing local shell scripts (e.g., .sh files) to encapsulate multi-step automation logic.
[COMMAND_EXECUTION]: The agent uses shell commands to interact with the moda CLI, manage file directories, and handle process logging through standard output redirection.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by processing external data without clear security boundaries.
Ingestion points: Data is pulled into the agent's context through actions like "read the pinned canvas" and "pull the source data" (SKILL.md).
Boundary markers: There are no instructions defining delimiters or explicit warnings to ignore potential commands embedded in the fetched data.
Capability inventory: The skill uses Bash(moda:*) and filesystem access to execute commands and write scripts based on the ingested content.
Sanitization: No sanitization, validation, or filtering processes are described for the content retrieved from external sources before it influences agent actions.

moda-automate