Polygraph litmus

We polygraph AI tools so you don’t have to. AI agents plug into third-party tools that can hijack them or leak your data. We run those tools through an adversarial test and publish a letter grade — free to read, public, evidence attached. 01 We test it. Adversarial probes in a sandbox — does it hijack the agent, overreach, or leak? 02 We grade it. A letter grade, A to F, published free with the evidence attached. 03 You check it. One command before your agent installs anything.