security-threat-model · tech-leads-club — Claude Code skill: threat model from your repo
security-threat-model reads your repository and writes a threat model: trust boundaries, assets, realistic abuse paths and mitigations, saved as a Markdown file.
Apache-2.0 ★ 7,191 updated 2026-10-24
npx skills add tech-leads-club/agent-skills --skill security-threat-model -a claude-codeWhat security-threat-model does
The skill reads a repository and builds the threat model from what the code actually shows. Every architectural claim needs evidence in the files, and assumptions get written down rather than hidden. Runtime behaviour is kept apart from CI, build tooling and tests.
The workflow runs in stages: scope and components, then trust boundaries with their protocol, auth and validation, then assets such as credentials and personal data, then entry points. After that come attacker capabilities and abuse paths, with priority derived from likelihood and impact and adjusted for controls already in place. The report format lives in references/prompt-template.md; an optional list of controls and assets sits in references/security-controls-and-assets.md, and only the files you need get loaded.
Before the final report it pauses and asks one to three questions: service owner and environment, deployment model, internet exposure, authentication, data sensitivity. Skip them and the ranking rests on assumptions, which makes the recommendations conditional. Output is a Markdown file named <repo-or-dir-name>-threat-model.md, taken from the repo or directory basename.
What it helps with
- Map trust boundaries in an unfamiliar repo
- List assets and entry points before a security review
- Rank which attacks on the service are realistic
- Tie each mitigation to a component or endpoint
- Hand the team a Markdown threat model to argue over
Example prompts for the agent
- Threat model the
services/authpath of this repo. - Enumerate abuse paths for the file upload endpoint and rank them.
- Write the threat model for
packages/ingestand save it as Markdown.
How to install security-threat-model
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill security-threat-model -a claude-code2Manually: put the files in place
~/.claude/skills/security-threat-model/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/security-threat-model/
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill security-threat-model -a codex2Manually: put the files in place
.agents/skills/security-threat-model/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill security-threat-model -a cursor2Manually: put the files in place
.cursor/skills/security-threat-model/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install tech-leads-club/agent-skills 'packages/skills-catalog/skills/(security)/security-threat-model'2Manually: put the files in place
.github/skills/security-threat-model/SKILL.md1Skills CLI (Vercel)
npx skills add tech-leads-club/agent-skills --skill security-threat-model -a gemini-cli2Platform CLI
gemini skills install https://github.com/tech-leads-club/agent-skills --path 'packages/skills-catalog/skills/(security)/security-threat-model'Manually: put the files in place
.devin/skills/security-threat-model/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about security-threat-model
How do I install security-threat-model in Claude Code?
Run npx skills add tech-leads-club/agent-skills --skill security-threat-model -a claude-code. The skill file ends up at ~/.claude/skills/security-threat-model/SKILL.md.
What does security-threat-model do?
It walks a repository or a chosen path and produces a threat model: components, entry points, assets, trust boundaries, abuse paths and mitigations, each with a priority.
Is this the same as a code review?
No. Reviewing code and giving general security advice are out of scope; the security-best-practices skill covers that side. This one models threats, and it waits for your answers about deployment and auth before it finalises the report.
Source text
SKILL.md · Apache-2.0
--- name: security-threat-model description: Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Use when the user asks to threat model a codebase or path, enumerate threats or abuse paths, or perform AppSec threat modeling. Do NOT use for general architecture summaries, code review, security best practices (use security-best-practices), or non-security design work. metadata: author: github.com/openai/skills version: '1.0.0' --- # Threat Model Source Code Repo Deliver an actionable AppSec-grade threat model that is specific to the repository or a project path, not a generic checklist. Anchor every architectural claim to evidence in the repo and keep assumptions explicit. Prioritizing realistic attacker goals and concrete impacts over generic checklists. ## Quick start 1. Collect (or infer) inputs: - Repo root path and any in-scope paths. - Intended usage, deployment model, internet exposure, and auth expectations (if known). - Any existing repository summary or architecture spec. - Use prompts in `references/prompt-template.md` to generate a repository summary. - Follow the required output contract in `references/prompt-template.md`. Use it verbatim when possible. ## Workflow ### 1) Scope and extract the system model - Identify primary components, data stores, and external integrations from the repo summary. - Identify how the system runs (server, CLI, library, worker) and its entrypoints. - Separate runtime behavior from CI/build/dev tooling and from tests/examples. - Map the in-scope locations to those components and exclude out-of-scope items explicitly. - Do not claim components, flows, or controls without evidence. ### 2) Derive boundaries, assets, and entry points - Enumerate trust boundaries as concrete edges between components, noting protocol, auth, encryption, validation, and rate limiting. - List assets that drive risk (data, credentials, models, config, compute resources, audit logs). - Identify entry points (endpoints, upload surfaces, parsers/decoders, job triggers, admin tooling, logging/error sinks). ### 3) Calibrate assets and attacker capabilities - List the assets that drive risk (credentials, PII, integrity-critical state, availability-critical components, build artifacts). - Describe realistic attacker capabilities based on exposure and intended usage. - Explicitly note non-capabilities to avoid inflated severity. ### 4) Enumerate threats as abuse paths - Prefer attacker goals that map to assets and boundaries (exfiltration, privilege escalation, integrity compromise, denial of service). - Classify each threat and tie it to impacted assets. - Keep the number of threats small but high quality. ### 5) Prioritize with explicit likelihood and impact reasoning - Use qualitative likelihood and impact (low/medium/high) with short justifications. - Set overall priority (critical/high/medium/low) using likelihood x impact, adjusted for existing controls. - State which assumptions most influence the ranking. ### 6) Validate service context and assumptions with the user - Summarize key assumptions that materially affect threat ranking or scope, then ask the user to confirm or correct them. - Ask 1–3 targeted questions to resolve missing context (service owner and environment, scale/users, deployment model, authn/authz, internet exposure, data sensitivity, multi-tenancy). - Pause and wait for user feedback before producing the final report. - If the user declines or can’t answer, state which assumptions remain and how they influence priority. ### 7) Recommend mitigations and focus paths - Distinguish existing mitigations (with evidence) from recommended mitigations. - Tie mitigations to concrete locations (component, boundary, or entry point) and control types (authZ checks, input validation, schema enforcement, sandboxing, rate limits, secrets isolation, audit logging). - Prefer specific implementation hints over generic advice (e.g., "enforce schema at gateway for upload payloads" vs "validate inputs"). - Base recommendations on validated user context; if assumptions remain unresolved, mark recommendations as conditional. ### 8) Run a quality check before finalizing - Confirm all discovered entrypoints are covered. - Confirm each trust boundary is represented in threats. - Confirm runtime vs CI/dev separation. - Confirm user clarifications (or explicit non-responses) are reflected. - Confirm assumptions and open questions are explicit. - Confirm that the format of the report matches closely the required output format defined in prompt template: `references/prompt-template.md` - Write the final Markdown to a file named `<repo-or-dir-name>-threat-model.md` (use the basename of the repo root, or the in-scope directory if you were asked to model a subpath). ## Risk prioritization guidance (illustrative, not exhaustive) - High: pre-auth RCE, auth bypass, cross-tenant access, sensitive data exfiltration, key or token theft, model or config integrity compromise, sandbox escape. - Medium: targeted DoS of critical components, partial data exposure, rate-limit bypass with measurable impact, log/metrics poisoning that affects detection. - Low: low-sensitivity info leaks, noisy DoS with easy mitigation, issues requiring unlikely preconditions. ## References - Output contract and full prompt template: `references/prompt-template.md` - Optional controls/asset list: `references/security-controls-and-assets.md` Only load the reference files you need. Keep the final result concise, grounded, and reviewable.
© github.com/openai/skills · Apache-2.0 · tech-leads-club/agent-skills
Similar skills
All skills for Security →security-threat-model by other authors comes first.