Ten short walkthroughs of Dethernety

Ten short videos are now on our YouTube channel, each showing one task in Dethernety. Most use a public demo application, so you can compare what the platform reports with the source.

Open the full playlist, or pick a video below.

Build the model

• A threat model generated from your repository (1:07). Dethereal, a plugin for AI coding agents, reads the code and proposes the model. Each element cites the file and line it came from.
• Building a threat model when there's no repo to read (1:41). Start from an empty canvas. Each question comes with a guide and, where one exists, a command that checks the answer.

Review the findings

• How many of your security findings are actually real? (1:25). AI agents review findings in groups against what the code says, and a person applies the verdicts.
• What can reach your crown jewels? (1:26). The threat report, with reachability and boundary crossings computed from the model.
• Assume breach: what can an attacker reach from here? (2:53). Pick a compromised component and walk through what it can reach.
• Your trust zones against your actual flows (1:32). Flows that cross a boundary, checked against the policy you declared.
• Your security controls, and what they actually cover (1:54). Record a control, answer what it depends on, and see which techniques it covers.

Turn findings into risks

• The evidence behind a risk rating, down to the CVE (2:17). From a cell in the risk matrix to the rule, the threat and its sources.
• Risks that live between your components (1:37). Checks on how components are arranged, such as a route to a critical asset with no detection on it.
• A risk register you can defend, line by line (1:39). The analysis drafts the risk. Your team sets the likelihood, owner and treatment.