SkillVaultskills Browse all 500 skills

Security · Version 1.4.0 · Reviewed 2026-08-02

Threat Modeling Agent

Find and prioritize exploitable risk in trust boundary mapping and attack enumeration with evidence, explicit trade-offs, and a verification plan.

4 method steps 6 documented failure modes 5 diagnostic checks 7 quality gates

Runs structured threat modeling over a design, enumerating trust boundaries, attacker goals, and mitigations.

₹99 one-time

Get this skill archive

What this skill helps you do

  • Trust boundary mapping
  • Attack enumeration
  • Mitigation prioritization

How Threat Modeling Agent works

You provide

Prompts, model versions, evaluation data, and failures

It inspects

Failure class and context sufficiency for trust boundary mapping

It decides

A attack enumeration change with one variable moved

You verify

Pass rate per case class against a pinned baseline

What it checks first

Threat Modeling Skill runs structured threat modeling over a design, enumerating trust boundaries, attacker goals, and mitigations. Use it when the work involves Trust boundary mapping, Attack enumeration, Mitigation prioritization.

  1. Whether the failure is systematic across a class of inputs or random, which separates a capability gap from a sampling issue.
  2. Whether evaluation data overlaps training or prompt-development data, which invalidates the measurement.
  3. Token distribution of inputs and outputs, since cost and latency are driven by the tail, not the mean.
  4. Whether the system has a defined behavior for low confidence, or always produces an answer.
  5. Version pinning across model, prompt, retrieval, and tools, because an unpinned component makes regressions unattributable.

Failure modes it recognizes

  • Silent quality regression after a provider updates a model behind an unversioned alias.
  • Evaluation overfitting where the prompt was tuned on the same examples used to score it.
  • Cost and latency dominated by a small number of very long inputs that were never in the test set.
  • Tool-calling loops where the model retries a failing tool without a bounded attempt budget.
  • Confident fabrication when context is insufficient because no refusal path was defined.
  • Distribution shift where production inputs diverge from the evaluation set over time.

Answers it will reject

  • Judging quality by reading a few outputs, which cannot detect a regression of a few percent.
  • Using a larger model to fix a problem caused by missing context, paying more for the same failure.
  • Fine-tuning before exhausting prompting and retrieval, which is slower to iterate and harder to reverse.
  • Using an LLM judge without validating the judge against human labels on the same rubric.

Decision rules it applies

  • Establish a labeled evaluation set and a baseline before changing anything; without a baseline there is no improvement, only change.
  • Pin every version and change one component at a time.
  • Define and test the refusal path explicitly; a system that cannot say "I do not know" will fabricate.
  • Budget latency and cost on p95 token counts, not averages.

Evidence it asks for

  • Score per input class (easy, hard, adversarial, no-answer) so aggregate scores cannot hide a broken class.
  • Log model version, prompt version, and retrieval version on every request for regression attribution.
  • Track p50 and p95 tokens and cost per successful task, not per call.

The method inside

  1. Map the artifact, actors, boundaries, and invariants relevant to trust boundary mapping.
  2. Trace concrete failure or abuse paths for attack enumeration; do not report checklist items without a mechanism.
  3. Prioritize mitigation prioritization findings by impact, likelihood, confidence, and cost of correction.
  4. Recommend the smallest defensible change, then define how an independent reviewer can verify it.

Deliverables

  • Trust boundary mapping assessment
  • Attack enumeration decision and action plan
  • Mitigation prioritization verification checklist

Evidence requirements

  • Code, configuration, data flows, and trust boundaries
  • Identity, authorization, and deployment context
  • Threat model, controls, and known assumptions

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Threat model our new file upload and sharing feature before we open it to external collaborators.

Expected output

Three trust boundaries matter here. The highest-severity path is an authenticated user escalating to another tenant through predictable share tokens, and the second is content served from a domain that shares cookies with your application, which turns any uploaded HTML into stored cross-site scripting...

Boundaries and compatibility

Ideal for

  • Trust boundary mapping: produce a decision or artifact grounded in supplied evidence.
  • Attack enumeration: produce a decision or artifact grounded in supplied evidence.
  • Mitigation prioritization: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Authorizing offensive actions against systems without permission
  • Reporting theoretical issues as exploitable without a path

Agent compatibility

  • GitHub Copilot custom agents
  • Claude Agent Skills / SKILL.md
  • Any instruction-following chat model

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.