Security

How messages from other agents retain their source and authority when delivered to your agent.

Messages from others

How a message from a schedule, a subagent or a teammate is told from yours.

  • A message from a schedule or a subagent reaches Link Harness with Link-From, is kept as from them, and the model is told who's speaking, with each line of it quoted, so no paragraph of it reads as yours: it's never taken as yours. A Link-From naming no sender is refused.
  • A stranger's message (one from neither the owner's own schedules, subagents and commands nor someone the owner let in: a webhook's) is given only the tools its spec's [tools] strangers names, none by default, and always says so, so its conversation never keeps more. A harness that can't narrow a conversation's tools never takes one.
  • It goes only to its own conversation, named as its sender, and is answered nowhere, so it never reads or narrows another and nothing it says reaches the owner's. Only the agent’s own spec sets strangers.
  • Through file, a conversation reads only its own folder of chats/, never another's, and a stranger's reads none, even when its spec grants it file. The tool's server checks each call against the conversation and standing the harness names, and refuses a call that names neither.
  • Stranger grants refuse the task, scheduler, run, and code namespaces, and agent__send, file__definition, file__references, and file__diagnostics. Those actions can run programs or send work as the agent, losing the stranger’s standing. Ordinary file reading and editing and agent__show remain eligible for explicit grants.
  • Every such message carries a hop count; the scheduler refuses one past the agent's cap ([tool.scheduler] hops, Link's 8). Hops bound how deep a chain goes, not how many messages it sends (each firing of a recurring job starts again): that's the cap a day ([tool.scheduler] per_day), with the cap on subagents at once, so agents can't wake each other for ever.
  • The scheduler runs as a tool, outside the agent's sandbox, confined to writing its jobs (~/Link/Agents/<agent>/agent/schedule). Which conversation a call is made in, and its hops, come from the harness (_meta), never from what the model writes, and a call lists and cancels only that conversation's jobs and its subagents'. The scheduler trusts what the harness sends:
  • Link Harness doesn't run what the model writes itself, and run's commands reach no tool, but a harness that does (a shell) could name another conversation or reset its hops, bounded then by the day's cap alone.
  • A subagent has its parent's tools or fewer, never more. The scheduler takes a list only of the tools the harness says the parent's conversation has (_meta link.local/tools), and, given none, the parent's whole list; the harness keeps the list with the subagent's conversation and narrows it again at each list, never widens it.
  • A harness that can't keep one isn't sent one: the bridge and the scheduler refuse it rather than send a subagent every tool it was meant not to have. The list bounds what the model is offered and calls; what each tool may do is still its grants'.
  • A subagent runs on the model it was started with, else its parent conversation's (_meta link.local/model), only ever one of the spec's [model] allow: Link Harness refuses another, and the model proxy names only those it was granted.
  • The bridge's way in is a Unix socket with the agent's settings (600), which only you reach, and each message at it is a call proved as the agent whose scheduler or run hands it (below).
  • An answer goes to an allowed user’s own chat on Telegram or Signal, the owner’s recorded direct chat with the bot on Slack or Discord, or a group an allowed user talked to the agent in. The bridge keeps recognized groups in the connection’s private folder and refuses group delivery with groups = "never".
  • Signal sends through the running bridge's send.sock in that folder (600), which takes a message only proved as its own agent's, with the key the machine's keyring holds for it still: a bridge outliving lnk agent stop takes nothing more. A Slack app or Discord bot connected before Link kept that sends no such answer until lnk agent connect again.