The Agent Skills Directory

[SAFE]: No security issues detected. The file provides documentation and payload examples for the cron tool.
[INDIRECT_PROMPT_INJECTION]: The skill documents how to schedule tasks that inject text into the agent's context. This represents a potential surface for indirect prompt injection if the scheduled content includes untrusted data, although the skill itself is purely instructional.
Ingestion points: payload.text and payload.message fields in the cron JSON examples within SKILL.md.
Boundary markers: Absent in documentation examples.
Capability inventory: The cron tool allows for scheduling recurring agent actions and system events.
Sanitization: Not applicable as this is a documentation-only skill.

cron-guide