Observed arrival · 2026-09-01

KuniNogu Maps the Seams Where AI Meets Permission

kuninogu.com Observed source

Editorial interest 82/100 Selection signal · not a rating of the site

Kuniyoshi Noguchi’s research site documents AI security, vulnerability disclosures, and detection engineering across agents, MCP servers, callbacks, and delegated authorization.

Landing page captured for the 2026-09-01 issue.

Field notes

The homepage frames AI security as an integration-layer problem rather than a model-weights problem, concentrating on permissions, tools, callbacks, and delegated authorization. Its evidence index lists six CVE credits and one vendor credit, including records for Splunk MCP Server, Apache Struts, @fastify/http-proxy, and Drupal AI components. The stated workflow pairs vulnerability findings with KQL, Sigma, or SPL material for Microsoft Sentinel and other defensive operations.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible

✦PrettyNotable craft visible

●ProPolished or operationally mature

◎NicheUnusually specific use

◉HumanPersonal, local, civic, or handmade

ƒJavaScriptBrowser-side code central

One card from the complete issue

Nobody Gets to See the Answer

315,616 arrived 1,000 judged 998 catalogued Enter the complete issue