Home / devcodex-labs / devcodex · GitHub

security-threat-modeling SKILL.md skillA

security-threat-modeling from devcodex-labs/devcodex is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add devcodex-labs/devcodex/security-threat-modeling@git:20260730.6ee304a

Pins git:20260730.6ee304a in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: devcodex-labs/devcodex
Path: content/skills/security-threat-modeling/SKILL.md
Versions recorded: 1
Latest version: git:20260730.6ee304a, committed Jul 30, 2026
Size: 5,648 bytes
Repository stars: 432
License: AGPL-3.0

安全威胁建模专家 Owner — 当任务涉及权限、认证、授权、输入输出信任边界、密钥策略、审计、攻击面、Webhook/OAuth、敏感操作或用户要求安全专家视角时使用；要求识别滥用路径并绑定缓解验证。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Security Threat Modeling Skill

## 定位

本 Skill 负责安全威胁建模 Owner 视角。它不默认改变 S02 用户策略，而是把信任边界、滥用路径、权限、审计和缓解验证说清楚。

## 触发条件

| 场景 | 是否触发 |
|------|:--------:|
| 认证、授权、权限、敏感操作、输入输出信任边界、审计、密钥策略 | 必须 |
| OAuth、Webhook、外部集成、admin、脚本执行、文件系统、数据库写入、发布凭据 | 必须 |
| 复审发现权限绕过、越权、注入、重放、审计缺失或风险误判 | 必须 |
| 纯文案或无安全边界变化 | N/A + skipReason |

## 核心门禁

| Gate | 要求 | 证据 |
|------|------|------|
| `SecurityThreatModelingGate` | 信任边界、威胁场景、权限滥用、密钥策略、审计和缓解验证必须成矩阵 | trustBoundary、threatScenario |
| `TrustBoundaryGate` | 输入、输出、调用方、外部系统和持久化边界必须明确 | trustBoundary |
| `PermissionAbuseCaseGate` | 权限滥用、越权、绕过和敏感操作必须有负向样例 | permissionAbuseCase |
| `SecretPolicyRespectGate` | 必须遵循 S02 用户 / 项目策略，不得自行加严 | secretPolicy |
| `AuditMitigationGate` | 缓解措施必须有日志、审计或测试证据 | auditLogging、mitigationVerification |
| `AuthorizedLocalSecurityAuditPresentationGate` | 用户自有/明确授权的本地安全审查也要分离“真实本地探针”与“用户可见呈现”；明确防御目标、最小必要证据和中断恢复，不得宣称绕过宿主安全控制 | authorizationContext、visibleEvidenceBudget、safetyInterruptionCard |

### AuthorizedLocalSecurityAuditPresentationGate

当安全审查目标是用户自有仓库、本地环境或已明确授权系统时，先记录 `authorizationContext`（所有权/授权、目标范围、允许动作、排除动作）与 `defensiveObjective`（识别、预防、修复、验证或恢复）。授权不能替代平台安全控制，也不能扩大用户未授权的外部目标。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add devcodex-labs/devcodex/security-threat-modeling@sha256:b21b07eb7f72497c

The line at the top of this page pins the label git:20260730.6ee304a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_n74zedm2sgq6phzz.svg)](https://markdownregistry.com/a/art_n74zedm2sgq6phzz)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jul 30, 2026.

version	committed	commit	size	audit
git:20260730.6ee304a latest	2026-07-30	6ee304a	5,648 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5648 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

devcodex-labs/devcodex · 432 stars · license AGPL-3.0 · pushed 2026-10-27 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_n74zedm2sgq6phzz
GET https://markdownregistry.com/api/v1/resolve?ref=devcodex-labs/devcodex/security-threat-modeling
GET https://markdownregistry.com/api/v1/blob/b21b07eb7f72497c6b6c307cc3fb70378698cf847db007870cc2115bf4b638eb

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from devcodex-labs/devcodex

accessibility-i18n SKILL.md skill

devcodex-labs/devcodex · content/skills/accessibility-i18n/SKILL.md · 无障碍与国际化专家 Owner — 当任务涉及可访问性、键盘操作、焦点、屏幕阅读器、ARIA、语言地区、本地化、RTL、翻译资源、用户可见文案或多语言文档时使用；要求把包容性体验和本地化验证绑定到真实用户路径。