yacine-kellib/agent-control-plane

A credential is not authorisation. ACP moves the authorise/refuse decision for AI agent actions outside the model, where prompt injection cannot reach it. Specification, Dafny proofs, and a reference implementation — every claim replays locally.

1 best points · 0 comments · 1 Hacker News post · 7 GitHub stars · View on GitHub

Hacker News discussions

• Agent Control Plane: the LLM proposes, it never authorizes (1 points, 0 comments, by Yacine_c75, 2026-08-17)