Topic
Undisclosed model routing
A service silently forwards user inputs to a different model or provider than the user believes they are using.
3 explicit connections
AI security research / concepts
Topics
Mechanisms and patterns across the research.
42 Topics · Page 3 of 3
2 matching records on this page
Published concepts
Topic
Website instructions promoted into agent authority
A website can place operational requests in llms.txt, HTTP headers or other retrieved metadata; the failure occurs when an agent treats that lower-trust content as permission for registration, installation or tool execution.
4 explicit connections
No matches on this page.