threat-modeling

threat-modeling is a cursor rule for Cursor from suyogpawar88/Threat-Model. It costs 55 tokens per session (839 once invoked), scanned A, original, MIT.

A security threat-modeling workflow for finding and assessing ways an application could be attacked. It covers standard methods such as STRIDE and PASTA, plus security risks specific to AI systems.

In plain words
What is it for?
Use it to analyze conventional, API, application, and AI infrastructure threats, including prompt injection, data poisoning, model extraction, and excessive agent permissions.
Why use it?
It turns a broad security review into a structured list of threats, risk scores, mappings, and possible safeguards.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Claude Code.

Good fit Use it to analyze conventional, API, application, and AI infrastructure threats, including prompt injection, data poisoning, model extraction, and excessive agent permissions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/suyogpawar88/threat-model/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/suyogpawar88/Threat-Model

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/suyogpawar88/threat-model/threat-modeling/github.svg)](https://agentmods.dev/rules/suyogpawar88/threat-model/threat-modeling)
Your own site
<a href="https://agentmods.dev/rules/suyogpawar88/threat-model/threat-modeling"><img src="https://agentmods.dev/badge/rules/suyogpawar88/threat-model/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/suyogpawar88/threat-model/threat-modeling"><img src="https://agentmods.dev/badge/rules/suyogpawar88/threat-model/threat-modeling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 839 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 $0.00055 $0.00839
Opus 5 $0.00028 $0.00419
Sonnet 5 $0.00011 $0.00168
Haiku 4.5 $0.00006 $0.00084

Measured 8d ago against content hash 60f6868f2217, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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.

.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.

Threat Modeling Rule

This project ships a full threat-modeling workflow originally packaged as a Claude Code / Cowork plugin. It works the same way here: read skills/threat-modeling/SKILL.md in full before starting, and follow it step by step. Do not skip straight to writing a threat list.

What this covers

  • STRIDE threat enumeration with Likelihood x Impact business-risk scoring (skills/threat-modeling/references/stride-methodology.md)
  • Optional full 7-stage PASTA process for higher-rigor engagements (skills/threat-modeling/references/pasta-methodology.md)
  • AI/ML/LLM infrastructure threats -- prompt injection, training/RAG data poisoning, model extraction, excessive agency, insecure output handling, unbounded consumption, etc. (skills/threat-modeling/references/ai-threat-taxonomy.md)
  • OWASP Top 10 (2021), OWASP API Security Top 10 (2023), and OWASP Top 10 for LLM Applications (2025) mapping for every threat (skills/threat-modeling/references/owasp-mappings.md)
  • MITRE ATT&CK (Enterprise) and MITRE ATLAS technique tagging for attack-chain steps (skills/threat-modeling/references/mitre-mappings.md)
  • Compensating-controls, mitigation-assurance, and compliance-gap analysis (skills/threat-modeling/references/compensating-controls-and-gaps.md)
  • Attack-chain / attack-scenario mapping (skills/threat-modeling/references/attack-chain-mapping.md)

How to run it here

  1. The four connectors (Jira, Jenkins, ServiceNow, code repo) are registered as MCP servers in .cursor/mcp.json -- enable them in Cursor's MCP settings and set the referenced environment variables (see .env.example / README.md). None are mandatory; the skill works with whatever subset is configured.
  2. Trigger this rule whenever the user asks to threat model a service, run STRIDE/PASTA, map threats to OWASP or MITRE, or produce a DFD/Word report/Excel risk register for a system -- including AI/LLM/agent systems.
  3. Follow skills/threat-modeling/SKILL.md Steps 1-9 exactly, using the report-data schema at skills/threat-modeling/references/report-data-schema.json and the worked examples in skills/threat-modeling/references/examples/ (sample_* for a conventional app, sample_ai_* for an AI/RAG/agent system).
  4. Render outputs by running the bundled scripts directly: python3 scripts/generate_drawio.py <spec.json> <output>.drawio [dfd|threat_model], python3 scripts/build_docx_report.py <report_data.json> <output>.docx, python3 scripts/build_xlsx_report.py <report_data.json> <output>.xlsx.
  5. For large connector payloads, pipe through python3 scripts/summarize.py --focus "..." first (requires ANTHROPIC_API_KEY) rather than reading raw payloads in full -- see scripts/requirements.txt for Python dependencies (pip install -r scripts/requirements.txt).

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. 8d ago First seen · 54 lines · 55 tokens per session scan A 60f6868f2217

Subscribe to this mod's changes

threat-modeling is a cursor rule published in the GitHub repository suyogpawar88/Threat-Model (6 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 839 once invoked, about $0.0003 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 2026-08-31.