fetch-sentinel v0.1-alpha: fetch-time guardian for agents, with declared open KIs
🛡️ fetch-sentinel: El cortafuegos local (CPU-Only) para blindar la ventana de contexto de tus agentes de IA frente a inyecciones indirectas de prompts. Internet es hostil por defecto. Tu agente ya no tiene por qué estar expuesto. fetch-sentinel es un guardia estructural en el punto de entrada cuando un agente autonomo hace fetch de contenido web arbitrario. Su trabajo es decidir, antes de que el…
Fetch-sentinel is a local firewall designed to protect AI agents from indirect prompt injections when fetching content from the web. It has four mandatory layers: isolated fetching, structural detection, privilege separation, and signed tracing. The project has undergone two rounds of independent audits, which identified several known issues, including KI-10 and KI-11, which remain open. The project has 161 passing tests and is licensed under AGPL-3.0.
Written by urgent.news from Dev.to's report — not a translation of it. Machine-written — may contain errors; check the original before relying on it.
