Tm7 Threat Model

Microsoft Threat Modeling Tool (.tm7) Generator

You generate valid .tm7 files for the Microsoft Threat Modeling Tool (v7.3+). A .tm7 file is not generic XML — it is a WCF DataContractSerializer document with an exact namespace and element structure. If the structure is wrong, the tool refuses to open the file with:

"File is not an actual threat model or the threat model may be corrupted."

Your job is to translate a described system (components, data stores, external actors, data flows, trust boundaries) into a diagram plus STRIDE threats, serialized in the exact .tm7 format described below.

When to invoke

• "Create a Microsoft Threat Modeling Tool .tm7 file."
• "Generate a STRIDE threat model that opens in the Microsoft Threat Modeling Tool."
• "Modify this .tm7 threat model."
• "Serialize this architecture as a valid TM7 file."
• "Fix a corrupted .tm7 threat model export."

Procedure

When asked to produce a .tm7 file:

1. Model the system. Identify the elements:
   • Processes (web apps, services, functions) → StencilEllipse, GE.P
   • Data stores (databases, caches, queues, blobs) → StencilParallelLines, GE.DS
   • External interactors (users, browsers, third-party systems) → StencilRectangle, GE.EI
   • Trust boundaries → BorderBoundary, GE.TB
   • Data flows connecting the above → Connector, GE.DF
2. Assign a unique lowercase UUID (e.g. 148ade68-5c80-40f3-8e1f-4e2cabdb5991) to every stencil and every flow. Never use human-readable ids like users-browser.
3. Lay out coordinates (Left/Top/Width/Height) so stencils don't overlap.
4. Generate STRIDE threats per interaction and place them in <ThreatInstances>.
5. Serialize using the structure in this guide, mirroring assets/example-minimal.tm7.
6. Validate against the "Common Mistakes" checklist before returning the file.
7. Write the file with no XML declaration and no pretty-print indentation (a single continuous XML stream is what the serializer emits).

Always open assets/example-minimal.tm7 first and adapt it — reuse its exact serialization skeleton and only change stencil types, names, coordinates, flows, and threats.

CRITICAL serialization format

TM7 files use WCF DataContractSerializer XML, not standard XML.

The file MUST start with this exact root element — no <?xml?> declaration:

<ThreatModel xmlns="http://schemas.datacontract.org/2004/07/ThreatModeling.Model" xmlns:i="http://www.w3.org/2001/XMLSchema-instance">

NEVER use:

• <?xml version="1.0" encoding="utf-8"?> — causes deserialization failure.
• xmlns:xsi / xmlns:xsd — these are standard XML namespaces, not DataContract namespaces.
• Invented elements such as <SecurityGaps> or <Mitigations> — they do not exist in the TM7 schema.

Note: <MetaInformation> (with children like <Owner>, <Contributors>, <Reviewer>, <Assumptions>, <ExternalDependencies>, <HighLevelSystemDescription>, <ThreatModelName>), <Notes>, and <KnowledgeBase> are part of the real schema and are emitted by the tool — keep them (see the structure below and assets/example-minimal.tm7). Just don't invent elements that the tool never produces.

Required namespace prefixes

File structure (correct order)

A full tool export contains, in this order: DrawingSurfaceList, MetaInformation, Notes, ThreatInstances, ThreatMetaData (often empty/self-closing), then the large generic KnowledgeBase as a top-level sibling (not nested inside ThreatMetaData), and finally Profile.

<ThreatModel xmlns="..." xmlns:i="...">
  <DrawingSurfaceList>
    <DrawingSurfaceModel z:Id="i1" xmlns:z="...">
      <GenericTypeId xmlns="...Abstracts">DRAWINGSURFACE</GenericTypeId>
      <Guid xmlns="...Abstracts">{guid}</Guid>
      <Properties xmlns="...Abstracts" xmlns:a="...Arrays">...</Properties>
      <TypeId xmlns="...Abstracts">DRAWINGSURFACE</TypeId>
      <Borders xmlns:a="...Arrays">
        <!-- Stencil elements: processes, data stores, external entities, boundaries -->
      </Borders>
      <Lines xmlns:a="...Arrays">
        <!-- Data flow lines connecting stencils -->
      </Lines>
      <Notes xmlns:a="...Arrays"/>
    </DrawingSurfaceModel>
  </DrawingSurfaceList>
  <MetaInformation>
    <!-- Owner, Contributors, Reviewer, Assumptions, ThreatModelName, etc. -->
  </MetaInformation>
  <Notes xmlns:a="...Arrays"/>
  <ThreatInstances>
    <!-- Threat entries -->
  </ThreatInstances>
  <ThreatMetaData/>
  <KnowledgeBase z:Id="i21" xmlns:a="...ThreatModeling.KnowledgeBase" xmlns:z="...">
    <!-- Generic SDL stencil/threat catalog — top-level sibling of ThreatMetaData -->
  </KnowledgeBase>
  <Profile>
    <PromptedKb xmlns=""/>
  </Profile>
</ThreatModel>

The <KnowledgeBase> (the generic SDL stencil/threat catalog) is large but required — the tool uses it to resolve every stencil TypeId. It is a top-level sibling placed after ThreatMetaData and before Profile, not nested inside ThreatMetaData. Reuse it verbatim from assets/example-minimal.tm7; only add stencils whose TypeId already appears in that KnowledgeBase.

Stencil elements

Each stencil in <Borders> is wrapped in <a:KeyValueOfguidanyType>:

<a:KeyValueOfguidanyType>
  <a:Key>{guid}</a:Key>
  <a:Value z:Id="i2" i:type="StencilEllipse">
    <GenericTypeId xmlns="...Abstracts">GE.P</GenericTypeId>
    <Guid xmlns="...Abstracts">{guid}</Guid>
    <Properties xmlns="...Abstracts">
      <a:anyType i:type="b:HeaderDisplayAttribute" xmlns:b="...KnowledgeBase">
        <b:DisplayName>Web Application</b:DisplayName>
        <b:Name/>
        <b:Value i:nil="true"/>
      </a:anyType>
      <a:anyType i:type="b:StringDisplayAttribute" xmlns:b="...KnowledgeBase">
        <b:DisplayName>Name</b:DisplayName>
        <b:Name/>
        <b:Value i:type="c:string" xmlns:c="http://www.w3.org/2001/XMLSchema">My Component</b:Value>
      </a:anyType>
      <!-- Out Of Scope, Reason, configurable attributes -->
    </Properties>
    <TypeId xmlns="...Abstracts">SE.P.TMCore.WebApp</TypeId>
    <Height xmlns="...Abstracts">100</Height>
    <Left xmlns="...Abstracts">400</Left>
    <StrokeDashArray i:nil="true" xmlns="...Abstracts"/>
    <StrokeThickness xmlns="...Abstracts">1</StrokeThickness>
    <Top xmlns="...Abstracts">200</Top>
    <Width xmlns="...Abstracts">100</Width>
  </a:Value>
</a:KeyValueOfguidanyType>

Stencil shape types

Common TypeId values (SDL TM knowledge base)

Data flow lines

Lines in <Lines> also use <a:KeyValueOfguidanyType>, with i:type="Connector":

<a:KeyValueOfguidanyType>
  <a:Key>{line-guid}</a:Key>
  <a:Value z:Id="i10" i:type="Connector">
    <GenericTypeId xmlns="...Abstracts">GE.DF</GenericTypeId>
    <Guid xmlns="...Abstracts">{line-guid}</Guid>
    <Properties xmlns="...Abstracts">...</Properties>
    <TypeId xmlns="...Abstracts">SE.DF.TMCore.Request</TypeId>
    <HandleX xmlns="...Abstracts">0</HandleX>
    <HandleY xmlns="...Abstracts">0</HandleY>
    <SourceGuid xmlns="...Abstracts">{source-stencil-guid}</SourceGuid>
    <SourceX xmlns="...Abstracts">0</SourceX>
    <SourceY xmlns="...Abstracts">0</SourceY>
    <TargetGuid xmlns="...Abstracts">{target-stencil-guid}</TargetGuid>
    <TargetX xmlns="...Abstracts">0</TargetX>
    <TargetY xmlns="...Abstracts">0</TargetY>
  </a:Value>
</a:KeyValueOfguidanyType>

Property attribute types

Properties use typed <a:anyType> elements:

Threat instances

Threats go in <ThreatInstances> using <a:KeyValueOfstringThreatpc_P0_PhOB> (note the exact PhOB suffix). Unlike stencils, the threat <a:Value> fields are b:-prefixed (the ThreatModeling.KnowledgeBase namespace), and the <a:Key> is the literal concatenation TH<id> + <SourceGuid> + <FlowGuid> + <TargetGuid>:

<ThreatInstances xmlns:a="...Arrays">
  <a:KeyValueOfstringThreatpc_P0_PhOB>
    <a:Key>TH117{source-guid}{flow-guid}{target-guid}</a:Key>
    <a:Value xmlns:b="...KnowledgeBase">
      <b:ChangedBy/>
      <b:DrawingSurfaceGuid>{drawing-surface-guid}</b:DrawingSurfaceGuid>
      <b:FlowGuid>{flow-guid}</b:FlowGuid>
      <b:Id>32</b:Id>
      <b:InteractionKey>{source-guid}:{flow-guid}:{target-guid}</b:InteractionKey>
      <b:InteractionString i:nil="true"/>
      <b:ModifiedAt>2025-01-01T00:00:00</b:ModifiedAt>
      <b:Priority>High</b:Priority>
      <b:Properties>
        <a:KeyValueOfstringstring>
          <a:Key>Title</a:Key>
          <a:Value>An adversary may spoof the user and gain access</a:Value>
        </a:KeyValueOfstringstring>
        <a:KeyValueOfstringstring>
          <a:Key>UserThreatCategory</a:Key>
          <a:Value>Spoofing</a:Value>
        </a:KeyValueOfstringstring>
        <a:KeyValueOfstringstring>
          <a:Key>UserThreatShortDescription</a:Key>
          <a:Value>Spoofing is when a process or entity is something other than its claimed identity.</a:Value>
        </a:KeyValueOfstringstring>
        <a:KeyValueOfstringstring>
          <a:Key>PossibleMitigations</a:Key>
          <a:Value>Enable multi-factor authentication and least-privilege access control.</a:Value>
        </a:KeyValueOfstringstring>
        <a:KeyValueOfstringstring>
          <a:Key>Priority</a:Key>
          <a:Value>High</a:Value>
        </a:KeyValueOfstringstring>
        <a:KeyValueOfstringstring>
          <a:Key>SDLPhase</a:Key>
          <a:Value>Design</a:Value>
        </a:KeyValueOfstringstring>
      </b:Properties>
      <b:SourceGuid>{source-stencil-guid}</b:SourceGuid>
      <b:State>Mitigated</b:State>
      <b:StateInformation i:nil="true"/>
      <b:TargetGuid>{target-stencil-guid}</b:TargetGuid>
      <b:Title i:nil="true"/>
      <b:TypeId>TH117</b:TypeId>
      <b:Upgraded>false</b:Upgraded>
      <b:Wide>false</b:Wide>
    </a:Value>
  </a:KeyValueOfstringThreatpc_P0_PhOB>
</ThreatInstances>

Every GUID must resolve: SourceGuid and TargetGuid must equal <a:Key> values of real stencils in <Borders>, and FlowGuid must equal the <a:Key> of a real connector in <Lines>. Dangling references produce a model that opens with missing diagram elements.

Use the standard STRIDE categories for UserThreatCategory: Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of Privilege.

Gotchas

1. Adding an <?xml version="1.0"?> declaration — DataContractSerializer does not emit one.
2. Using xmlns:xsi / xmlns:xsd instead of DataContract namespaces.
3. Using simple element names like <Border>, <Line>, <Stencil> — you must use the DataContract wrapper types such as <a:KeyValueOfguidanyType>.
4. Inventing elements the tool never emits like <SecurityGaps> or <Mitigations> — these are not in the schema. (<MetaInformation>, <Notes>, and <KnowledgeBase> are valid and must be preserved.)
5. Using human-readable GUIDs like users-browser instead of real UUIDs (e.g. 148ade68-5c80-40f3-8e1f-4e2cabdb5991).
6. Dangling references — a Line, threat SourceGuid/TargetGuid, or threat FlowGuid that points to a stencil/flow GUID that isn't actually defined in <Borders>/<Lines>. Every reference must resolve to an included element.
7. Missing or duplicated z:Id reference attributes — every serialized object needs a z:Id, and each z:Id (e.g. i1, i2, i10) must be unique across the whole file. When you duplicate a template block to add an element, always renumber its z:Id (and any nested ones) to values not used elsewhere; reusing an id creates duplicate DataContract object ids and makes deserialization fail.
8. Missing the xmlns on child elements — each GenericTypeId, Guid, Properties, TypeId, etc. must carry its own xmlns="http://schemas.datacontract.org/2004/07/ThreatModeling.Model.Abstracts".
9. Pretty-printing with indentation — the correct output is a single continuous XML stream with no added newlines or indentation inside the content.

Progressive disclosure and bundled resources

At discovery time, only name and description are loaded. Read the bundled asset only when a .tm7 file must be generated or repaired.

• assets/example-minimal.tm7: synthetic Microsoft Threat Modeling Tool v7.3+ export with two stencils, one data flow, one STRIDE threat, valid namespaces, valid z:Id references, and a reusable KnowledgeBase.

Reference asset

Always use assets/example-minimal.tm7 in this skill's directory as the structural reference. It is a fully synthetic, sanitized export (no personal or project data) that opens cleanly in the tool: two stencils connected by one data flow, with one STRIDE threat whose every reference resolves. Adapt the stencil types, names, properties, coordinates, data flows, and threats to the user's architecture, but never change the serialization format or namespace structure, and only use stencil TypeId values that already appear in its bundled KnowledgeBase. After generating, mentally diff your output's skeleton against the example to confirm every namespace, wrapper element, and GUID reference matches.

Output template

## TM7 threat model result

**Status:** generated | modified | blocked
**File:** `<path/to/model.tm7>`
**Model:** <ThreatModelName>

| Element type | Count | TypeIds used | Notes |
| --- | ---: | --- | --- |
| Processes | <count> | `SE.P.TMCore.WebApp` | <notes> |
| Data stores | <count> | `SE.DS.TMCore.SQL` | <notes> |
| External interactors | <count> | `SE.EI.TMCore.Browser` | <notes> |
| Trust boundaries | <count> | `GE.TB` | <notes> |
| Data flows | <count> | `SE.DF.TMCore.Request` | <notes> |
| Threats | <count> | `TH117` | <STRIDE categories covered> |

**Validation**
- Root element: pass | fail
- DataContract namespaces: pass | fail
- GUID references resolve: pass | fail
- Unique `z:Id` values: pass | fail
- `KnowledgeBase` preserved after `ThreatMetaData`: pass | fail

Quality gate

• The file starts with <ThreatModel xmlns="http://schemas.datacontract.org/2004/07/ThreatModeling.Model" xmlns:i="http://www.w3.org/2001/XMLSchema-instance"> and has no XML declaration.
• DrawingSurfaceList, MetaInformation, Notes, ThreatInstances, ThreatMetaData, top-level KnowledgeBase, and Profile appear in the correct order.
• Every stencil and connector uses a unique lowercase UUID and every object uses a unique z:Id.
• Every SourceGuid, TargetGuid, FlowGuid, and InteractionKey resolves to real <Borders> and <Lines> entries.
• Stencil i:type, GenericTypeId, and TypeId values come from the bundled assets/example-minimal.tm7 KnowledgeBase.
• STRIDE threats use a:KeyValueOfstringThreatpc_P0_PhOB, b:-prefixed threat fields, and standard UserThreatCategory values.
• The generated .tm7 is a single continuous XML stream with no added pretty-print indentation.

References

• ThreatModeling.Model namespace
• ThreatModeling.Model.Abstracts namespace
• ThreatModeling.KnowledgeBase namespace
• Serialization namespace
• Serialization arrays namespace
• XML Schema namespace
• XML Schema instance namespace