Runtime security enforcement and capability scoping for agents

Show HN: Runtime security enforcement and capability scoping for agents

Runtime security enforcement and capability scoping for agents is a business in show hn launch.

Profile

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 break out of them. We've found vulnerabilities across over a dozen agent providers and frameworks (practically every one we tested) displaying this behavior (eg. a model fraudulently splitting payments to avoid a company-set payment limit, multi-model agent teams infecting each with injections, MCP rug pulls, etc).We've developed an architecture that does two things: 1) instead of setting a sandbox for a session and le

Its activity falls under show hn launch; the profile below is assembled from public directory data.

Its current recorded stage is Show HN launch.

Website: www.clayseal.com