[{"data":1,"prerenderedAt":341},["ShallowReactive",2],{"article-\u002Fblog\u002Ffeature-walkthroughs":3,"related-\u002Fblog\u002Ffeature-walkthroughs":147},{"id":4,"title":5,"author":6,"body":8,"date":133,"description":134,"extension":135,"image":136,"meta":137,"navigation":138,"path":139,"seo":140,"stem":141,"tags":142,"video":145,"__hash__":146},"blog\u002Fblog\u002Ffeature-walkthroughs.md","Ten short walkthroughs of Dethernety",{"name":7},"dether.net",{"type":9,"value":10,"toc":126},"minimark",[11,15,25,30,50,54,96,100],[12,13,14],"p",{},"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.",[12,16,17,24],{},[18,19,23],"a",{"href":20,"rel":21},"https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLtJoQ7XAI5qduQNQtBnaWhTFayEMxsXjn",[22],"nofollow","Open the full playlist",", or pick a video below.",[26,27,29],"h2",{"id":28},"build-the-model","Build the model",[31,32,33,42],"ul",{},[34,35,36,41],"li",{},[18,37,40],{"href":38,"rel":39},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=NfSfJ7IbIDY",[22],"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.",[34,43,44,49],{},[18,45,48],{"href":46,"rel":47},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qr0WX1S9WA4",[22],"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.",[26,51,53],{"id":52},"review-the-findings","Review the findings",[31,55,56,64,72,80,88],{},[34,57,58,63],{},[18,59,62],{"href":60,"rel":61},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4RQ71ZxuJ4Y",[22],"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.",[34,65,66,71],{},[18,67,70],{"href":68,"rel":69},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=G9bbcaW84l0",[22],"What can reach your crown jewels?"," (1:26). The threat report, with reachability and boundary crossings computed from the model.",[34,73,74,79],{},[18,75,78],{"href":76,"rel":77},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=jjLG-oXhFM8",[22],"Assume breach: what can an attacker reach from here?"," (2:53). Pick a compromised component and walk through what it can reach.",[34,81,82,87],{},[18,83,86],{"href":84,"rel":85},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=70QQTiozNzg",[22],"Your trust zones against your actual flows"," (1:32). Flows that cross a boundary, checked against the policy you declared.",[34,89,90,95],{},[18,91,94],{"href":92,"rel":93},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=K8Uu22rGrTQ",[22],"Your security controls, and what they actually cover"," (1:54). Record a control, answer what it depends on, and see which techniques it covers.",[26,97,99],{"id":98},"turn-findings-into-risks","Turn findings into risks",[31,101,102,110,118],{},[34,103,104,109],{},[18,105,108],{"href":106,"rel":107},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=77nNfDmBqJs",[22],"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.",[34,111,112,117],{},[18,113,116],{"href":114,"rel":115},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=f4sfrsO04Sg",[22],"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.",[34,119,120,125],{},[18,121,124],{"href":122,"rel":123},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=U_irtZjwR54",[22],"A risk register you can defend, line by line"," (1:39). The analysis drafts the risk. Your team sets the likelihood, owner and treatment.",{"title":127,"searchDepth":128,"depth":128,"links":129},"",2,[130,131,132],{"id":28,"depth":128,"text":29},{"id":52,"depth":128,"text":53},{"id":98,"depth":128,"text":99},"2026-09-06","Ten videos of one to three minutes, each showing one task: building a model, reviewing its findings, or turning them into risks.","md","\u002Fimages\u002Fblog\u002Fpost-walkthroughs.jpg",{},true,"\u002Fblog\u002Ffeature-walkthroughs",{"title":5,"description":134},"blog\u002Ffeature-walkthroughs",[143,144],"video","platform","NfSfJ7IbIDY","FhFoKaHicXHxYvu65noOdsntEqulx0IOT271Dbm_H30",[148,303],{"id":149,"title":150,"author":151,"body":152,"date":291,"description":292,"extension":135,"image":293,"meta":294,"navigation":138,"path":295,"seo":296,"stem":297,"tags":298,"video":301,"__hash__":302},"blog\u002Fblog\u002Fbyodt-available.md","BYODt is available",{"name":7},{"type":9,"value":153,"toc":286},[154,157,161,228,231,234,238,241,244,247,251,265],[12,155,156],{},"You can now subscribe to BYODt (Bring Your Own Dethernety). You run the platform on your own infrastructure, and we serve specialized module packages to it from our cloud.",[26,158,160],{"id":159},"editions-and-prices","Editions and prices",[162,163,164,183],"table",{},[165,166,167],"thead",{},[168,169,170,174,177,180],"tr",{},[171,172,173],"th",{},"Edition",[171,175,176],{},"Seats",[171,178,179],{},"Includes",[171,181,182],{},"Price per month",[184,185,186,201,215],"tbody",{},[168,187,188,192,195,198],{},[189,190,191],"td",{},"BYODt",[189,193,194],{},"1",[189,196,197],{},"The packages you choose",[189,199,200],{},"EUR 25 per package",[168,202,203,206,209,212],{},[189,204,205],{},"BYODt Team 5",[189,207,208],{},"5",[189,210,211],{},"Every technology package",[189,213,214],{},"EUR 199",[168,216,217,220,223,225],{},[189,218,219],{},"BYODt Team 20",[189,221,222],{},"20",[189,224,211],{},[189,226,227],{},"EUR 499",[12,229,230],{},"Five packages are available: AWS, Azure, Containers & Kubernetes, Self-Managed Infrastructure, and Agentic AI. Every package also includes Risk Assessment, Dethereal Triage and the Threat Patterns engine, and Agentic AI adds the patterns it runs. Team editions include packages published later at no extra cost.",[12,232,233],{},"Prices exclude VAT. Billing is monthly, and you can cancel at any time. We sell to businesses only, and we check a team's tax number before its first purchase where a register can be asked.",[26,235,237],{"id":236},"what-leaves-your-network","What leaves your network",[12,239,240],{},"Your models and findings stay in your platform. When you ask for an evaluation, your deployment sends the configured attributes of a single element, meaning the answers to that class's form. Most answers are yes\u002Fno or a fixed choice, but some are free-form values, such as a role ARN or a policy document. We run the policy over those values in memory, return the result, and keep neither the input nor the output.",[12,242,243],{},"We do not record which class you asked about, and no request carries a deployment identifier. We do know who you are and when your deployment asked for something, because users sign in against our identity service, and we meter request volume per team. Accounts and content are hosted in the EU.",[12,245,246],{},"AI clients are separate. Dethereal and Triage run in your coding agent, which sends what they read to the model provider you configure.",[26,248,250],{"id":249},"how-to-start","How to start",[12,252,253,254,259,260,264],{},"The platform stays free and open source, so you can ",[18,255,258],{"href":256,"rel":257},"https:\u002F\u002Fdocs.dether.net\u002Fplatform\u002Fquick-start\u002F",[22],"run it first",". There is no self-serve trial. If you would like an evaluation, ",[18,261,263],{"href":262},"\u002Fcontact","contact us"," and we can arrange access.",[12,266,267,268,273,274,279,280,285],{},"To subscribe, ",[18,269,272],{"href":270,"rel":271},"https:\u002F\u002Fbyodt.dethernety.io\u002Fofferings",[22],"see the plans"," or read the ",[18,275,278],{"href":276,"rel":277},"https:\u002F\u002Fdocs.dether.net\u002Fbyodt-subscription\u002F",[22],"subscription guide",". Our ",[18,281,284],{"href":282,"rel":283},"https:\u002F\u002Fbyodt.dethernety.io\u002Fdpa",[22],"data processing terms"," are published on the portal.",{"title":127,"searchDepth":128,"depth":128,"links":287},[288,289,290],{"id":159,"depth":128,"text":160},{"id":236,"depth":128,"text":237},{"id":249,"depth":128,"text":250},"2026-11-04","BYODt (Bring Your Own Dethernety): host the platform yourself and get module packages served from our cloud. From EUR 25 per package per month.","\u002Fimages\u002Fhero-graph.jpeg",{},"\u002Fblog\u002Fbyodt-available",{"title":150,"description":292},"blog\u002Fbyodt-available",[299,300],"announcement","editions",null,"0pl5wM45wf4HqdM7miwYeVFnxrOuymxcuYyH2n18uhE",{"id":304,"title":305,"author":306,"body":307,"date":330,"description":331,"extension":135,"image":332,"meta":333,"navigation":138,"path":334,"seo":335,"stem":336,"tags":337,"video":339,"__hash__":340},"blog\u002Fblog\u002Fthreat-modeling-agentic-architectures.md","Threat modeling agentic architectures: two new videos",{"name":7},{"type":9,"value":308,"toc":328},[309,312,320],[12,310,311],{},"Two new videos cover threat modeling for AI agents. Both use a fictional support copilot whose tickets arrive from the internet.",[12,313,314,319],{},[18,315,318],{"href":316,"rel":317},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=pzeDZ8YaLAU",[22],"Threat modeling of agentic architectures"," (6:56) is for people working on AI agents, copilots and their tools. It starts with threats inside one component, such as an agent acting without human approval, then moves to threats across components. It draws on two cases from MITRE ATLAS: a package posing as an e-mail service's MCP server, which began copying every e-mail it sent to the attacker (AML.CS0053), and the PromptArmor demonstration against Slack AI (AML.CS0035). The second half models the copilot in Dethernety and goes through its findings, open questions, fixes and the summary page for the CISO.",[12,321,322,327],{},[18,323,326],{"href":324,"rel":325},"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BF7OMnhj6qg",[22],"How a support AI can leak customer data with zero clicks"," (1:34) is the short version, with captions. It follows one attack on the copilot. A ticket hides an instruction to add customer details to an image link in the reply. When a staff member opens the draft, the console loads the image by itself, which sends the data to the attacker's server. Nobody has to click the link.",{"title":127,"searchDepth":128,"depth":128,"links":329},[],"2026-10-16","A seven-minute video and a 90-second short on threat modeling AI agents, using a fictional support copilot.","\u002Fimages\u002Fblog\u002Fpost-agentic.jpg",{},"\u002Fblog\u002Fthreat-modeling-agentic-architectures",{"title":305,"description":331},"blog\u002Fthreat-modeling-agentic-architectures",[143,338],"agentic AI","pzeDZ8YaLAU","szjbpIFycX9vuzKXN9ZWLnw8vR0RJAsbsbHhG1RjDa8",1793814258327]