The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-supplied strings which are stored and later re-injected into the agent's context as prompts. This constitutes an indirect prompt injection surface.
Ingestion points: The --prompt argument in the letta cron add command.
Boundary markers: Absent; the content is passed back to the agent as a message.
Capability inventory: The agent can execute shell commands via the letta cron CLI tool.
Sanitization: No sanitization or verification of the scheduled prompt content is performed by the skill instructions.- [COMMAND_EXECUTION]: The skill uses the letta cron CLI tool to create and manage scheduled tasks. These commands are executed locally using a Bash tool and are part of the ecosystem provided by the skill author.

scheduling-tasks