threat-modeling-mcp-server: Skill for Kiro

.kiro/skills/phase-7-5-code-validation/SKILL.md

phase-7-5-code-validation is a skill for Kiro from awslabs/threat-modeling-mcp-server. It costs 32 tokens per session (554 once invoked), scanned A, original, Apache-2.0.

A guide for checking whether recorded threats and mitigations are supported by evidence in the actual source code. Evidence means specific findings from reviewing the implementation.

In plain words
What is it for?
Use it to record findings, mark threats and mitigations as fully, partly, or not addressed, check for missing or outdated evidence, and generate a validation report.
Why use it?
It connects the planned security analysis to what the code really does and highlights threats or protections that still lack current evidence.

Skill for Kiro ✓ vendor

Written for Kiro: installed under .kiro/.

This is awslabs/threat-modeling-mcp-server's own configuration. It tells Kiro how to work on threat-modeling-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything threat-modeling-mcp-server configures →

About the project

Threat Modeling MCP Server is an MCP server that guides an AI coding agent through structured security threat modeling and code validation. It analyzes business context, architecture, assets, trust boundaries, and threat actors, then produces Markdown or JSON reports using a phased STRIDE-based process. The catalogue skills operate this workflow through compatible agent clients.

awslabs/threat-modeling-mcp-server · 100 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to awslabs/threat-modeling-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/awslabs/threat-modeling-mcp-server/main/.kiro/skills/phase-7-5-code-validation/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/awslabs/threat-modeling-mcp-server

Made for: Kiro.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for phase-7-5-code-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/awslabs/threat-modeling-mcp-server/phase-7-5-code-validation.svg)](https://agentmods.dev/skills/awslabs/threat-modeling-mcp-server/phase-7-5-code-validation)
Your own site
<a href="https://agentmods.dev/skills/awslabs/threat-modeling-mcp-server/phase-7-5-code-validation"><img src="https://agentmods.dev/badge/skills/awslabs/threat-modeling-mcp-server/phase-7-5-code-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00554
Opus 5 $0.00016 $0.00277
Sonnet 5 $0.00006 $0.00111
Haiku 4.5 $0.00003 $0.00055

Measured 8d ago against content hash 61f766043c67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

phase-7-5-code-validation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.kiro/skills/phase-7-5-code-validation/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 7.5: Code Validation Analysis

Objective

Inspect the implementation and record evidence for every current threat and mitigation. This phase runs only when source code is detected in the project recorded with manage_workflow(action="set_project").

Tool

manage_code_validation(action, values=None)

Action Purpose
describe Show the finding payload and accepted outcomes
record Atomically store findings and update canonical statuses
get Show current findings, missing IDs, and stale records
validate Check that every current threat and mitigation has fresh evidence
report Render the evidence-based report and finalize the current snapshot
clear Remove findings before starting a new validation

record accepts values.threat_findings and values.mitigation_findings. Each finding requires its record ID, an outcome, and at least one non-empty evidence string. recommendation is optional.

Threat outcomes:

  • fully_mitigated
  • partially_mitigated
  • not_mitigated
  • not_applicable

Mitigation outcomes:

  • implemented
  • partially_implemented
  • not_implemented
  • not_applicable

Workflow

  1. Call manage_workflow(action="guidance", phase="7.5").
  2. Call manage_code_validation(action="describe").
  3. Inspect the relevant files and identify concrete file, line, configuration, or test evidence.
  4. Call manage_code_validation(action="record", values=FINDINGS). Findings may be submitted incrementally.
  5. Call manage_code_validation(action="validate"); record every missing or stale item.
  6. Call manage_code_validation(action="report") to finalize the current snapshot.
  7. Call manage_workflow(action="advance") to proceed to Phase 8.

Observed code behavior belongs in finding evidence. Use manage_assumptions(action="add", values=ASSUMPTION) only when a statement remains unverified.

Completion Criteria

  • Every current threat has a fresh finding
  • Every current mitigation has a fresh finding
  • Each finding contains concrete evidence or a not-applicable rationale
  • Validation reports complete coverage
  • The final report has been generated for the current snapshot
  • manage_workflow(action="advance") proceeds to Phase 8

Read the full file on GitHub · 59 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 59 lines · 32 tokens per session scan A 61f766043c67

Subscribe to this mod's changes

phase-7-5-code-validation is a skill published in the GitHub repository awslabs/threat-modeling-mcp-server (100 stars, last pushed 12d ago), licensed Apache-2.0. It adds 32 tokens to every session and 554 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.