ai-security-crew: Command for Claude Code

.claude/commands/threat-model.md

threat-model is a command for Claude Code from Srajangpt1/ai-security-crew. It costs 0 tokens per session (1,241 once invoked), scanned A, original, MIT.

A developer-focused analysis of how a feature or component could be attacked. It maps likely threats to the provided code, data flows, technologies, and system boundaries.

In plain words
What is it for?
Use it to assess a planned feature, describe realistic attack paths in plain language, and connect each risk to evidence from the supplied architecture or code.
Why use it?
Thinking through concrete attack scenarios before implementation can reveal weaknesses in authentication, file handling, external services, or sensitive data flows.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is Srajangpt1/ai-security-crew's own configuration. It tells Claude Code how to work on ai-security-crew 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 ai-security-crew configures →

Part of the mcp-security-review plugin — 3 skills, 3 commands, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Srajangpt1/ai-security-crew. 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/Srajangpt1/ai-security-crew/main/.claude/commands/threat-model.md
Clone the repo
git clone --depth 1 https://github.com/Srajangpt1/ai-security-crew

Made for: Claude Code.

Or install mcp-security-review, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 1 MCP server.

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 threat-model

README.md
[![agentmods](https://agentmods.dev/badge/commands/srajangpt1/ai-security-crew/threat-model/github.svg)](https://agentmods.dev/commands/srajangpt1/ai-security-crew/threat-model)
Your own site
<a href="https://agentmods.dev/commands/srajangpt1/ai-security-crew/threat-model"><img src="https://agentmods.dev/badge/commands/srajangpt1/ai-security-crew/threat-model/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for threat-model

Your own site · 80×15
<a href="https://agentmods.dev/commands/srajangpt1/ai-security-crew/threat-model"><img src="https://agentmods.dev/badge/commands/srajangpt1/ai-security-crew/threat-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,241 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.
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 $0.00000 $0.01241
Opus 5 $0.00000 $0.00620
Sonnet 5 $0.00000 $0.00248
Haiku 4.5 $0.00000 $0.00124

Measured 9d ago against content hash cad8544470d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

threat-model 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 9d 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.

.claude/commands/threat-model.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Perform a threat model for the following feature or component:

$ARGUMENTS


Instructions

Produce a developer-focused threat model for the feature or component described above. If no description is provided, ask the user:

  1. What are they building? (feature name + description)
  2. What tech stack is involved?
  3. Are there code snippets, data flows, or architecture notes to analyze?

Write threats in plain language — describe concrete attack scenarios a developer would understand, not abstract STRIDE categories. Every threat must link to evidence from the artifacts provided.

Step 1 — Understand What We're Building

Extract from the input:

  • Feature/component name — what is this thing?
  • Description — what does it do, what problem does it solve?
  • Tech stack — languages, frameworks, databases, cloud services
  • Data touched — what data flows through this feature? (credentials, PII, payment data, tokens, internal config, etc.)
  • System boundaries — what calls this? what does it call? external vs internal?
  • Architecture notes — deployment model, trust boundaries, network zones

Step 2 — Identify Security Signals

Scan the description and any provided artifacts for:

Attack surfaces:

  • Authentication endpoints (login, registration, password reset, OAuth)
  • File upload / download handlers
  • External API integrations (third-party services, webhooks)
  • Admin / privileged operations
  • Data exports or bulk operations
  • Cross-tenant operations in multi-tenant systems
  • Unauthenticated or public endpoints

Sensitive data patterns:

  • Credentials and secrets (passwords, API keys, tokens)
  • PII (names, emails, phone numbers, addresses)
  • Financial data (card numbers, account numbers, transactions)
  • Health data (PHI, medical records)
  • Internal configuration or infrastructure details

Technology-specific risks:

  • JWT: algorithm confusion, none-algorithm, token theft, refresh token abuse
  • OAuth: redirect URI manipulation, CSRF on callback, token leakage in logs
  • SQL databases: injection, excessive permissions, unencrypted sensitive columns
  • File handling: path traversal, unrestricted upload, SSRF via URL fetch
  • Redis/caching: cache poisoning, insecure TTLs, unauthenticated access
  • Microservices: service-to-service auth, internal SSRF, broken trust boundaries
  • Webhooks: signature validation, replay attacks, SSRF via callback URLs

Read the full file on GitHub · 137 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. 9d ago First seen · 137 lines · 0 tokens per session scan A cad8544470d6

Subscribe to this mod's changes

threat-model is a command published in the GitHub repository Srajangpt1/ai-security-crew (68 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,241 tokens. 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.