threat-model-review

threat-model-review is a skill for Claude Code from RedHatProductSecurity/agentic-threat-modeling. It costs 37 tokens per session (1,355 once invoked), scanned A, original, Apache-2.0.

A review tool that compares an existing threat model with the current codebase. It checks whether the documented risks and assumptions still match the software and its surrounding systems.

In plain words
What is it for?
Use it to find removed threats, new attack surfaces, changed assumptions, and mitigations that have not been implemented.
Why use it?
Threat models become outdated as features, dependencies, integrations, and security controls change. This review highlights what is stale, missing, or still unfinished.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to find removed threats, new attack surfaces, changed assumptions, and mitigations that have not been implemented.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review
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 RedHatProductSecurity/agentic-threat-modeling --skill threat-model-review
Clone the repo
git clone --depth 1 https://github.com/RedHatProductSecurity/agentic-threat-modeling

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 threat-model-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review/github.svg)](https://agentmods.dev/skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review)
Your own site
<a href="https://agentmods.dev/skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/agentic-threat-modeling/threat-model-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,355 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 $0.00037 $0.01355
Opus 5 $0.00018 $0.00678
Sonnet 5 $0.00007 $0.00271
Haiku 4.5 $0.00004 $0.00136

Measured 12d ago against content hash 554b91a1bfea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

threat-model-review 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 12d 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.

module/skills/threat-model-review/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Threat Model Review

You review existing threat models to determine if they're still accurate and complete. Threat models decay — code changes, new features ship, dependencies update, infrastructure evolves. Your job is to identify what's drifted.

Workflow

1. Find and Parse the Existing Threat Model

  • Locate THREAT_MODEL.md at the path specified (default: repository root)
  • Parse all sections: system context, threats, mitigations, assumptions, provenance
  • Note the date it was last updated and the scope it covers

2. Analyze Code Changes

Compare the current codebase against what the threat model describes:

New attack surface:

  • New API endpoints not covered in the entry points section
  • New data stores or external integrations
  • New authentication/authorization mechanisms
  • New deployment configurations (containers, cloud services)
  • New dependencies (check package manifests for additions)

Removed components:

  • Endpoints, services, or integrations that were removed
  • Threats tied to removed components are now stale

Modified components:

  • Changes to auth flows, data handling, or API contracts
  • Infrastructure changes (new network segments, changed deployment model)
  • Dependency updates that may resolve or introduce vulnerabilities

3. Check Threat Currency

For each threat in the existing model:

Still valid?

  • Does the affected component still exist?
  • Is the attack vector still exposed?
  • Has the vulnerability been patched or mitigated?

Risk changed?

  • Have new controls been added that reduce likelihood?
  • Has the blast radius changed (more data, more users, higher sensitivity)?
  • Has the threat landscape shifted (new CVEs, new attack techniques)?

Stale?

  • Component was removed or completely rewritten
  • Mitigation was fully implemented
  • The assumption it was based on is no longer true

4. Check Mitigation Status

For each recommended mitigation in the existing model:

  • Has it been implemented? (Look for evidence in code: rate limiting added, MFA implemented, encryption enabled)
  • Is it partially implemented?
  • Is it still relevant? (The threat it addresses may have changed)

Read the full file on GitHub · 144 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. 12d ago First seen · 144 lines · 37 tokens per session scan A 554b91a1bfea

Subscribe to this mod's changes

threat-model-review is a skill published in the GitHub repository RedHatProductSecurity/agentic-threat-modeling (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,355 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 2026-08-31.