Real incidents. Reproducible attacks. Practical defenses. How something trusted becomes an attack surface: what happened, how to detect it, and what to change.https://poisoned.dev/enWed, 07 Oct 2026 00:00:00 GMThttps://poisoned.dev/articles/zero-trust-postmortem/https://poisoned.dev/articles/zero-trust-postmortem/A Zero Trust postmortem of the OpenAI and Hugging Face incident. The evaluation sandboxes had no internet access, yet the agents reached the internet anyway, through a package proxy that had it, and turned the proxy's cache into a meeting place. The lesson is a way of seeing: a security boundary is a capability graph, a map of what can reach what, through whom, including the edges nobody drew.Wed, 07 Oct 2026 00:00:00 GMTagentszero trustsecurity architecturemulti-agenthttps://poisoned.dev/articles/please-honor-commit/https://poisoned.dev/articles/please-honor-commit/Agents that kept their promises to each other still breached two organisations. Three rules an evaluation harness must enforce: discovery is not permission, provenance is not authority, and the subject does not hold its own evidence.Wed, 30 Sep 2026 00:00:00 GMTagentsevaluationsupply chainhttps://poisoned.dev/articles/why-poisoned/https://poisoned.dev/articles/why-poisoned/Most AI security failures are the same story: something you trusted stopped being trustworthy, and nothing in the pipeline told you.Mon, 28 Sep 2026 00:00:00 GMTsupply chaineditorial