Notes on AI security: prompt injection, agent permission blast radius, tenant isolation, and what to actually look for in a review.https://wannerlabs.comen-ushttps://wannerlabs.com/blog/adr-uber-mit-speed-of-riskhttps://wannerlabs.com/blog/adr-uber-mit-speed-of-riskWhat ADR is, why Uber built it with MIT, what ten months of production deployment found, and why the defender’s clock now runs at machine speed.Wed, 05 Aug 2026 05:00:00 GMTai-securityagent-securitymcphttps://wannerlabs.com/blog/prompt-injection-for-code-reviewhttps://wannerlabs.com/blog/prompt-injection-for-code-reviewWhy prompt injection in LLM agents needs the same review discipline as SQL injection did twenty years ago, and where to actually look for it in a PR.Fri, 31 Jul 2026 00:00:00 GMTai-securityprompt-injectioncode-review