AGPL-3.0-or-later · forever.

the journal · by tag

Security

Every post filed under Security, newest first — one register of 7 the journal keeps. The shelf lens on the journal filters the same set in place.

  • 4postsin this register
  • 7tagsthe journal keeps
  • 33posts in the journalall registers together
  • 2026-07-08latestnewest first below
04The prompt injection that goes nowherePrompt injection examples usually end with the agent taking a new action. Here the plan is authored before the model runs: the hostile note becomes data, never an action, and the boundary is checked before a token is spent.2026-07-08 · 3 min03The credentials your pipeline was breakingOpenAI and Google sign the images their APIs return. Almost every pipeline that touches those files silently converts the signature into evidence of tampering. That included ours, until this week.2026-07-06 · 4 min02The secrets lineInformation-flow, audited before it flows: how the checker proves a secret cannot leak into a prompt, a file, or a host.2026-07-05 · 3 min01The blast radius is part of the filepermits: is the whole list, guardrails an agent can't talk past. Everything not on it is denied before it runs, with a named error.2026-06-04 · 1 min

The other registers: Engine · Agents · Language · Sovereignty · Manifesto · Origins. The whole journal →