Show HN: Runtime security enforcement and capability scoping for agents

By pberlizov · 2026-07-08 · 2 points · 0 comments

https://www.clayseal.com

Hi everyone. We're AI researchers at Harvard and Carnegie Mellon working on a project to advance the state of agent security. Currently, many systems rely on static sandboxing, which in long-running sessions enables agents to understand the safeguards holding them in place and b…

Open the full discussion on BetterNews