New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Assess Application Threat Model

by cyberful in cyberful/cyberful

Build or challenge an application threat model from architecture, dataflows, identities, trust boundaries, business invariants, dependencies, and deployment context.

AGPL-3.0Auto-check passedSecurity

Install Assess Application Threat Model

skills CLI
$ npx skills add cyberful/cyberful --skill assess-application-threat-model -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cyberful/cyberful assess-application-threat-model --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/assess-application-threat-model .claude/skills/assess-application-threat-model && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
assess-application-threat-model
GitHub stars
135
Token cost
~1.2k tokens
SKILL.md length
474 words
Files
4 (incl. references)
Skills in repo
85
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Build or challenge an application threat model from architecture, dataflows, identities, trust boundaries, business invariants, dependencies, and deployment context.

  • Works in 4 steps: What are we building or assessing? → What can go wrong? → What will prevent, detect, contain, or… → …
  • Code-audit planning
  • SKILL.md covers Answer the four questions, Model the system, Start from unacceptable outcomes and Elicit threats with multiple…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Assess Application Threat Model is an agent skill from cyberful/cyberful. Build or challenge an application threat model from architecture, dataflows, identities, trust boundaries, business invariants, dependencies, and deployment context. Use for design reviews, code-audit planning, pentest hypothesis generation, feature changes, abuse-case discovery, control requirements, architecture assessment, or residual-risk analysis.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/elicitation-catalog.md` and `references/model-quality.md`).

It sits in Security, covering Threat modeling, Penetration testing and Hypothesis generation. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.

When your agent uses it

  • Code-audit planning
  • Pentest hypothesis generation
  • Feature changes
  • Abuse-case discovery

Example prompts

  • “/assess-application-threat-model”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. What are we building or assessing?
  2. What can go wrong?
  3. What will prevent, detect, contain, or recover from it?
  4. How will we know the model and controls are good enough?

What it can do on your machine

Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • owasp.org
    • threatmodelingmanifesto.org
    • csrc.nist.gov
    • capec.mitre.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Assess Application Threat Model loads about 1.2k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 474 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 474 words, ~1,199 tokens.

Download SKILL.mdSave it as .claude/skills/assess-application-threat-model/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
assess-application-threat-model
description
Build or challenge an application threat model from architecture, dataflows, identities, trust boundaries, business invariants, dependencies, and deployment context. Use for design reviews, code-audit planning, pentest hypothesis generation, feature changes, abuse-case discovery, control requirements, architecture assessment, or residual-risk analysis.
metadata.domain
application-security
metadata.subdomain
threat-modeling
metadata.triggers
application threat model, architecture threat review, abuse case model, trust boundary analysis, security design review
metadata.tags
threat-modeling, STRIDE, attack-trees, trust-boundaries, security-requirements

Assess an Application Threat Model

Produce a model that participants recognize as the real system and that generates testable security requirements. Do not produce a generic STRIDE checklist detached from architecture.

Answer the four questions

  1. What are we building or assessing?
  2. What can go wrong?
  3. What will prevent, detect, contain, or recover from it?
  4. How will we know the model and controls are good enough?

Model the system

Capture:

  • assets and unacceptable outcomes;
  • actors, identities, roles, tenants, assurance levels, and machine principals;
  • processes, data stores, queues, caches, browsers, clients, build systems, and external services;
  • dataflows with protocol, parser, authentication context, sensitivity, and direction;
  • trust boundaries, privilege transitions, administrative planes, and human approvals;
  • lifecycle states, revocation, failure modes, retries, fallback, recovery, and decommissioning;
  • assumptions about networks, callers, providers, model behavior, and deployment configuration.

Read references/elicitation-catalog.md for structured threat elicitation. Use references/model-quality.md to challenge completeness.

Start from unacceptable outcomes

Express outcomes in product language:

  • another tenant's data or authority becomes reachable;
  • identity is created, linked, recovered, or elevated without required evidence;
  • money, inventory, quota, entitlement, or approval changes outside the business invariant;
  • untrusted content controls an interpreter, parser, fetcher, tool, build, or deployment;
  • secrets or sensitive data cross an unintended audience, persistence, or retention boundary;
  • one actor can impose disproportionate compute, storage, cost, fan-out, or operational load;
  • audit, revocation, or recovery cannot reconstruct and contain the event.

Then work backward to attack paths and forward to controls.

Elicit threats with multiple lenses

Apply only relevant lenses:

  • STRIDE to each trust boundary and dataflow;
  • authorization and tenant matrix to every resource and action;
  • state-machine and abuse-case review to business workflows;
  • privacy and data-lifecycle review to every copy;
  • kill-chain or attack-tree decomposition to high-value outcomes;
  • CAPEC/CWE/OWASP catalogs to avoid known blind spots;
  • supply-chain and deployment review to pre-runtime authority;
  • agentic-AI review to instruction, memory, retrieval, output, and tool boundaries.

Catalogs supplement adversarial reasoning; they do not replace it.

Show full SKILL.md (156 more words)Show less

Convert threats into requirements

For each material threat record:

threat | preconditions | path | affected asset/invariant | preventive control | detective/recovery control | owner | verification method | residual risk

Make requirements specific and testable. Prefer "service verifies tenant membership against the authoritative resource on every mutation" over "implement access control." Identify the enforcement layer and failure behavior.

Derive tests and code-review targets

Translate each threat into at least one negative test, control inspection, monitoring assertion, or recovery exercise. Route dynamic tests to the authorized pentest ledger and static tests to concrete entry points, policies, and sinks. Preserve threats whose verification requires unavailable environments as explicit residual uncertainty.

Maintain the model

Revisit when identity, dataflow, parser, dependency, privilege, deployment, tool authority, business state, or external integration changes. Link model elements to code, configuration, tests, owners, and findings so the model is reviewable rather than ornamental.

Authoritative anchors

© cyberful, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in cyberful/builtin/skills/assess-application-threat-model of cyberful/cyberful.

  • SKILL.md
  • agents/openai.yaml
  • references/elicitation-catalog.md
  • references/model-quality.md

Open the folder on GitHubat commit ec598a6

Compare with similar skills

Assess Application Threat Model next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Assess Application Threat Model compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Assess Application Threat Model this skillcyberful/cyberful135—~1.2kAutomated safety check: PassAGPL-3.0
Secure By Designooiyeefei/ccc495—~1.5kAutomated safety check: PassMIT
Graph DB Writessamugit83/redamon3k—~2.2kAutomated safety check: PassMIT
Csono-session/pstack136—~12kAutomated safety check: NotesMIT
Senior Securitydavila7/claude-code-templates33k2 repos~1.1kAutomated safety check: NotesMIT
Threat Model Disciplinehypnguyen1209/offensive-claude388—~660Automated safety check: PassMIT

Similar skills

  • Secure By Design

    ooiyeefei/ccc

    Run an enterprise security review of a system design or existing code before it ships.

    495 GitHub stars~1.5k tokensUpdated 2 mo ago
    SecurityAuto-check passed

  • Graph DB Writes

    samugit83/redamon

    Writing to the Neo4j attack-surface graph in RedAmon: the tenant-isolation MERGE key every entity node must carry, where graph methods live (mixins, not the client), and the schema places that must…

    3k GitHub stars~2.2k tokensUpdated 2 days ago
    SecurityAuto-check passed

  • Cso

    no-session/pstack

    Chief Security Officer mode. An agent skill from no-session/pstack.

    136 GitHub stars~12k tokensUpdated 6 mo ago
    SecurityAuto-check: notes

  • Senior Security

    davila7/claude-code-templates

    Comprehensive security engineering skill for application security, penetration testing, security architecture, and compliance auditing.

    33k GitHub starsUsed in 2 repos~1.1k tokens
    SecurityAuto-check: notes

  • Threat Model Discipline

    hypnguyen1209/offensive-claude

    A skill your agent uses when starting an engagement, before exploitation, or whenever the attack surface changes — build/validate the threat model and detect drift (new unreviewed surface) before…

    388 GitHub stars~660 tokensUpdated 13 days ago
    SecurityAuto-check passed

  • Security

    telagod/code-abyss

    Defensive security engineering judgment, distilled from a stronger model - invoke when THREAT MODELING a system or feature; making security-relevant design decisions (auth, crypto, trust boundaries…

    244 GitHub stars~907 tokensUpdated 2 mo ago
    SecurityAuto-check passed

More from cyberful/cyberful

All 85 skills in this repo

  • Audit Infrastructure As Code

    cyberful/cyberful

    Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.

    135 GitHub stars~649 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Kubernetes Policy Enforcement

    cyberful/cyberful

    Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.

    135 GitHub stars~610 tokensUpdated 1 mo ago
    Auto-check passed

  • Audit Pci Dss Penetration Test Evidence

    cyberful/cyberful

    Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.

    135 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Content Discovery

    cyberful/cyberful

    Design and interpret advanced content discovery with ffuf and complementary web fuzzers.

    135 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Network Recon

    cyberful/cyberful

    Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.

    135 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Operate Sast Toolchain

    cyberful/cyberful

    Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.

    135 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Assess Application Threat Model

What does Assess Application Threat Model do?

Build or challenge an application threat model from architecture, dataflows, identities, trust boundaries, business invariants, dependencies, and deployment context. Assess Application Threat Model is an agent skill from cyberful/cyberful. Build or challenge an application threat model from architecture, dataflows, identities, trust boundaries, business invariants, dependencies, and deployment context.

When should I use Assess Application Threat Model?

Assess Application Threat Model fits situations like: code-audit planning; pentest hypothesis generation; feature changes; abuse-case discovery.

How do I install Assess Application Threat Model in Claude Code?

Run `npx skills add cyberful/cyberful --skill assess-application-threat-model -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/assess-application-threat-model in cyberful/cyberful) into .claude/skills/assess-application-threat-model in your project. Claude Code loads it when a task matches its description.

How do I install Assess Application Threat Model in Codex?

Run `npx skills add cyberful/cyberful --skill assess-application-threat-model -a codex`. Or copy the skill folder (cyberful/builtin/skills/assess-application-threat-model in cyberful/cyberful) into .agents/skills/assess-application-threat-model in your project. Codex loads it when a task matches its description.

Can I use Assess Application Threat Model in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill assess-application-threat-model -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assess-application-threat-model, .gemini/skills/assess-application-threat-model, .github/skills/assess-application-threat-model and .opencode/skills/assess-application-threat-model in your project.

What does Assess Application Threat Model need to run?

SKILL.md names no scripts, command-line tools or credentials: Assess Application Threat Model is instructions for the agent only.

Does Assess Application Threat Model access the network?

SKILL.md names 4 domains. As links in the text: owasp.org, threatmodelingmanifesto.org, csrc.nist.gov and capec.mitre.org. This is read from the text; nothing was executed.

Is Assess Application Threat Model safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Assess Application Threat Model use?

Assess Application Threat Model is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Assess Application Threat Model use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Assess Application Threat Model?

Skills that share tags, products or a category with Assess Application Threat Model: Secure By Design (ooiyeefei/ccc, 495 stars), Graph DB Writes (samugit83/redamon, 3k stars), Cso (no-session/pstack, 136 stars) and Senior Security (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Assess Application Threat Model?

cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.

Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.