security-threat-model

security-threat-model is a skill for Claude Code from euxx/claude-skills-for-copilot. It costs 82 tokens per session (1,635 once invoked), scanned A, original, MIT.

A repository-based security analysis that maps trust boundaries, valuable data, attacker abilities, abuse paths, and protections.

In plain words
What is it for?
Creating a concise Markdown threat model for a codebase or project path, including realistic attacks, impacts, mitigations, and remaining risks.
Why use it?
It turns the codebase’s actual structure into a focused security plan instead of relying only on generic checklists.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Creating a concise Markdown threat model for a codebase or project path, including realistic attacks, impacts, mitigations, and remaining risks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/euxx/claude-skills-for-copilot/security-threat-model
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.

Any agent
npx skills add euxx/claude-skills-for-copilot --skill security-threat-model
Clone the repo
git clone --depth 1 https://github.com/euxx/claude-skills-for-copilot

Made for: Claude Code.

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 security-threat-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/euxx/claude-skills-for-copilot/security-threat-model/github.svg)](https://agentmods.dev/skills/euxx/claude-skills-for-copilot/security-threat-model)
Your own site
<a href="https://agentmods.dev/skills/euxx/claude-skills-for-copilot/security-threat-model"><img src="https://agentmods.dev/badge/skills/euxx/claude-skills-for-copilot/security-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 security-threat-model

Your own site · 80×15
<a href="https://agentmods.dev/skills/euxx/claude-skills-for-copilot/security-threat-model"><img src="https://agentmods.dev/badge/skills/euxx/claude-skills-for-copilot/security-threat-model.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,635 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 $0.00082 $0.01635
Opus 5 $0.00041 $0.00817
Sonnet 5 $0.00016 $0.00327
Haiku 4.5 $0.00008 $0.00163

Measured 11d ago against content hash 409f95ea4273, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

security-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 11d 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.

skills/security-threat-model/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Threat Model

Deliver an actionable AppSec-grade threat model specific to the repository or a project path. Anchor every architectural claim to evidence in the repo; keep assumptions explicit. Prioritize realistic attacker goals and concrete impacts over generic checklists.

Quality rules (apply throughout)

  • Evidence-grounded: every component, data flow, or control must be backed by at least one repo path and, where helpful, a symbol name, config key, or short quoted snippet. Do not invent components.
  • No secrets in output: if you find tokens, keys, or passwords, redact them and describe their presence and location only.
  • Scope discipline: separate production/runtime behavior from CI/build/dev tooling and from tests/examples. Separate attacker-controlled inputs from operator-controlled and developer-controlled inputs.
  • Concise for AppSec engineers: use precise terminology; include mitigations and residual risks; avoid restating large blocks of README/spec.

Workflow

1. Collect inputs

Ask the user (or infer and mark as assumptions):

  • Intended usage and deployment model (server, CLI, library, worker)
  • Internet exposure (public, internal, air-gapped)
  • Authentication / authorization expectations
  • Data sensitivity (PII, credentials, financial, public)
  • Any explicitly out-of-scope paths

If the user provided a path argument, scope the model to that sub-path.

2. Explore the repo

Use file search, grep -rI (skip binaries), or ripgrep rg (skips binaries by default) to locate security-relevant surfaces:

  • Network listeners, routes, endpoints, RPC handlers, message consumers
  • Auth, session/token handling, RBAC/ACL logic
  • Parsing/deserialization (JSON/YAML/XML/protobuf), template rendering, eval
  • File upload/read paths, archive extraction, image/document parsing
  • Database, queue, and cache clients and query construction
  • Secrets/config loading, environment variables, key management
  • SSRF-capable HTTP clients, webhooks, URL fetchers
  • Sandboxing, privilege boundaries, subprocess execution
  • Logging/error handling paths
  • CI/build pipelines, dependency management, artifact publishing

Read the full file on GitHub · 183 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. 11d ago First seen · 183 lines · 82 tokens per session scan A 409f95ea4273

Subscribe to this mod's changes

security-threat-model is a skill published in the GitHub repository euxx/claude-skills-for-copilot (4 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,635 once invoked, about $0.0004 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.