{"version":"2.1.280","anchor":"teammate-messages-are-now-flagged-verifiedforgedunverifiab","canonical_anchor":"teammate-messages-are-now-flagged-verifiedforgedunverifiab","heading":"Teammate and swarm messages now get a verified\/forged provenance check","tier":"notice","area":"Teammates","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/teammate-messages-are-now-flagged-verifiedforgedunverifiab","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### Teammate and swarm messages now get a verified\/forged provenance check\n\nClaude Code now checks whether a teammate's message really came from who it claims, and treats spoofed messages differently\n\n**What**\n\n- Incoming messages between teammates (in a team or swarm session) are now classified as `verified` (the message ID matches what the sender actually wrote), `forged`, or `unverifiable`, based on whether the claimed sender is a legitimate in-process or leader-pane teammate.\n\n- The team inbox poller now checks this before acting on a message: forged messages are kept separate from trusted plan-approval\/permission-response handling and are shown to the model with a `verified=\"false\"` attribute so it knows the sender's identity wasn't confirmed.\n\n- The swarm mailbox poller similarly checks provenance before accepting a `shutdown_request` or `plan_approval_response` from a message; forged messages are skipped rather than acted on, with new bookkeeping (`consumedUnmarked`) to avoid reprocessing messages already filtered as forged.\n\n- Summary\/text-block handling now also treats a `forged` item the same way it treats an already-summarized one.\n\n**Why** This stops a spoofed message from impersonating a teammate to trigger sensitive actions like approving a plan or shutting down a session, while still surfacing unverified messages to the model with a clear warning instead of silently dropping them.\n\n- Area: Teammates\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5"}