The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the imsg command-line utility to perform its core functions including reading history and sending messages via the macOS Messages.app.- [INDIRECT_PROMPT_INJECTION]: The skill reads message content from external senders which introduces a surface for indirect prompt injection.
Ingestion points: Incoming messages are ingested into the agent context through the imsg history and imsg watch commands as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to distinguish between message data and system instructions.
Capability inventory: The agent has the capability to send outgoing messages using imsg send and can interact with local files via the --file attachment flag.
Sanitization: There is no evidence of filtering or sanitization of message content before it is processed by the agent.

imessage