openai-security-threat-model — Claude Code plugin for threat modeling
The openai-security-threat-model plugin examines a repository for security threats and writes a concise Markdown model. Use it when you explicitly want to assess a codebase or path.
Apache-2.0 ★ 540 updated 2026-07-14
/plugin marketplace add trailofbits/skills-curated
/plugin install openai-security-threat-model@skills-curatedWhat openai-security-threat-model does
The plugin maps trust boundaries, assets, and attacker capabilities, then identifies abuse paths and mitigations. Its output is a concise Markdown threat model grounded in the repository.
It activates when asked directly to model threats for a codebase or path, enumerate threats, or perform AppSec threat modeling. A general architecture summary or routine code review will not trigger it, so make the security request explicit.
What it helps with
- map trust boundaries in a repository
- identify assets and attacker capabilities
- trace abuse paths through code
- record mitigations in a threat model
Example prompts for the agent
- Create a Markdown threat model for this repository, including trust boundaries and abuse paths.
- Enumerate security threats in
src/authand suggest mitigations. - Perform AppSec threat modeling for this codebase.
How to install openai-security-threat-model
Plugin marketplace
/plugin marketplace add trailofbits/skills-curated/plugin install openai-security-threat-model@skills-curatedStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about openai-security-threat-model
How do I install openai-security-threat-model in Claude Code?
Run these commands in order: /plugin marketplace add trailofbits/skills-curated, then /plugin install openai-security-threat-model@skills-curated.
What does openai-security-threat-model do?
It examines a repository's trust boundaries, assets, attacker capabilities, and abuse paths, then produces a concise Markdown threat model with mitigations.
Will it run during a general code review?
No. It activates on an explicit request for threat modeling; a general architecture summary or routine code review does not trigger it.
Source text
openai-security-threat-model · Apache-2.0
# Security Threat Model Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work. ## Installation ``` /plugin install trailofbits/skills-curated/plugins/openai-security-threat-model ``` ## What It Covers - Quick start - Workflow - Risk prioritization guidance (illustrative, not exhaustive) - References ## Credits Originally from [OpenAI's curated skills catalog](https://github.com/openai/skills/tree/main/skills/.curated/security-threat-model). Converted to Claude Code plugin format for the Trail of Bits curated skills marketplace.
© OpenAI · Apache-2.0 · trailofbits/skills-curated