Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Threat Modeler Skill · a5c-ai | DecimalAI

securityby a5c-ai

Threat Modeler Skill

a5c-ai/threat-modeler

Source a5c-ai/babysitter ↗License MIT

Generate threat models using STRIDE, PASTA, or VAST methodologies

SkillScore83Maintained

Automatic

Security & AppSec pack

Last verified 8/30/2026

What it changes

Passed 20 of 24 test cases with the skill, and 14 of 24 without it.

Without skill58%

With skill83%

Checks it passed that the model alone missed

Calculates threat prioritization scores using DREAD.
Rates threat risk scores using the DREAD methodology.
Evaluates threat risk scores using DREAD scoring metrics.

and 4 more in the full report

6 fixed14 passed either way4 still failing0 broke

Pass-rate lift: +25 pp
Tokens: +20%
Agent turns: 0%
Response time: +4%

Model gemini-3.6-flashMeasured 8/30/2026v120 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/a5c-ai-threat-modeler/SKILL.md https://app.decimal.ai/s/a5c-ai-threat-modeler/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add a5c-ai-threat-modeler, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/a5c-ai-threat-modeler/ and pins it in .decimal/skills.lock

decimalai skills add a5c-ai-threat-modeler

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/a5c-ai-threat-modeler/SKILL.md https://app.decimal.ai/s/a5c-ai-threat-modeler/SKILL.md

Raw file: /s/a5c-ai-threat-modeler/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-threat-modeler.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

We are conducting a security architecture review for our new telehealth patient portal API. The system includes an API gateway, an authentication server, a patient record database, and external web clients. Data flows include patient credentials from web clients to the gateway and medical records moving between the gateway and database across internal network trust boundaries. Please perform a threat modeling analysis using the STRIDE methodology. Include a full list of identified threats with risk scores, affected assets, and actionable mitigations, along with generated attack trees, a visual DFD representation, and a summary breakdown by severity.

What was checked, without and with the skill
Checked	Without skill	With skill
Calculates threat risk scores using DREAD methodology parameters.	Missed	Passed
Includes a summary breakdown of threat counts grouped by category.	Missed	Passed

case-01 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md133 linessingle file

Threat Modeler Skill

Overview

Generates threat models using STRIDE, PASTA, or VAST methodologies with attack tree generation, data flow diagram analysis, and threat prioritization using DREAD.

Capabilities

Generate STRIDE threat models
PASTA methodology support
VAST methodology support
Attack tree generation
Data flow diagram analysis
Threat prioritization (DREAD)
Microsoft Threat Modeling Tool integration
Mitigation recommendations

Target Processes

security-architecture-review
api-design-specification

Input Schema

{
  "type": "object",
  "required": ["system"],
  "properties": {
    "system": {
      "type": "object",
      "properties": {
        "name": { "type": "string" },
        "description": { "type": "string" },
        "dataFlows": { "type": "array" },
        "assets": { "type": "array" },
        "trustBoundaries": { "type": "array" },
        "externalEntities": { "type": "array" }
      }
    },

Track record

Benchmark

20 / 24

test cases passed, vs 14 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/specializations/software-architecture/skills/threat-modeler/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Threat Modeler Skill

Overview

Capabilities

Target Processes

Input Schema

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills