threat-modeling

threat-modeling is a cursor rule for Cursor from Oriolshhh/runware-image-mcp. It costs 13 tokens per session (505 once invoked), scanned A, original, MIT.

A structured security review that maps what must be protected, who might attack it, where data crosses trust boundaries, and how an attack could happen.

In plain words
What is it for?
Use it for changes involving untrusted input, authentication, secrets, filesystem or command execution, dependencies, generated files, or untrusted instructions.
Why use it?
It replaces vague security concerns with ranked threats, concrete exploit paths, and specific mitigations. It helps reveal risks such as injection, secret exposure, unsafe file access, and compromised dependencies.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it for changes involving untrusted input, authentication, secrets, filesystem or command execution, dependencies, generated files, or untrusted instructions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/oriolshhh/runware-image-mcp/threat-modeling
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Cursor.

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-modeling

README.md
[![agentmods](https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/threat-modeling/github.svg)](https://agentmods.dev/rules/oriolshhh/runware-image-mcp/threat-modeling)
Your own site
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/threat-modeling"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/threat-modeling/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-modeling

Your own site · 80×15
<a href="https://agentmods.dev/rules/oriolshhh/runware-image-mcp/threat-modeling"><img src="https://agentmods.dev/badge/rules/oriolshhh/runware-image-mcp/threat-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00013 $0.00505
Opus 5 $0.00006 $0.00253
Sonnet 5 $0.00003 $0.00101
Haiku 4.5 $0.00001 $0.00051

Measured 6d ago against content hash 28d5ca374369, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

threat-modeling 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 6d 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.

.cursor/rules/threat-modeling.mdc · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: threat-modeling

Threat Modeling

Purpose

Reason systematically about how a change could be abused, so security findings are concrete and prioritized rather than generic.

When to use it

  • For changes touching untrusted input, auth, secrets, filesystem/command execution, dependencies, generated-file ownership, or untrusted instructions.
  • During the /council security review.

Instructions

  1. List the assets worth protecting (data, credentials, integrity of generated files, execution surface).
  2. List the actors (users, other services, malicious input, compromised deps) and the entry points they reach.
  3. Draw the trust boundaries the change crosses; note where untrusted data becomes trusted.
  4. Enumerate misuse cases: injection, traversal/symlink escape, privilege misuse, secret exposure, supply-chain tampering, prompt injection.
  5. For each realistic threat, give the exploit path, severity, and a concrete mitigation. Separate vulnerabilities (exploitable now) from optional hardening.
  6. Decide whether a fuller, standalone threat model is warranted.

Output format

A threat model: assets, actors, entry points, trust boundaries, ranked threats (each with exploit path, severity, mitigation), vulnerabilities vs. hardening, and residual risk.

Anti-patterns

  • Generic checklists with no exploit path or repository evidence.
  • Labelling optional hardening as a live vulnerability (or vice versa).
  • Naming secret values instead of the configuration key or source.
  • Stopping at "validate input" without identifying the specific sink.

Verification checklist

  • Trust boundaries and entry points are explicit.
  • Each threat has an exploit path, severity, and concrete mitigation.
  • Vulnerabilities and hardening are clearly separated.
  • The need for a formal threat model is decided, with reasons.

Read the full file on GitHub · 54 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. 6d ago First seen · 54 lines · 13 tokens per session scan A 28d5ca374369

Subscribe to this mod's changes

threat-modeling is a cursor rule published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 505 once invoked, about $0.0001 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 2026-09-03.