← 返回 Skills 市场
123
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install threat
功能描述
Deep threat modeling workflow—system decomposition, trust boundaries, STRIDE-style threats, mitigations, prioritization, and tracking. Use when designing new...
安全使用建议
This skill is a high-level facilitator for threat-modeling workshops and is internally consistent with that purpose. Because it is instruction-only (no installs or required secrets), it has a low technical footprint. Before using it: avoid pasting real secrets (API keys, private keys, or PII) into the chat or outputs; confirm any artifacts the agent generates are stored according to your team policy; and prefer explicit, on-demand invocation rather than long-running or automated runs if you want tighter control over what project information the agent can access. If you need the agent to integrate with ticketing or issue trackers, review those integration steps separately for required credentials and scope.
功能分析
Type: OpenClaw Skill
Name: threat
Version: 1.0.0
The skill bundle consists of a structured methodology for performing threat modeling (STRIDE) and contains no executable code, network requests, or suspicious instructions. The content in SKILL.md is purely educational and procedural, aligning with its stated purpose of guiding an agent through security architecture reviews.
能力评估
Purpose & Capability
Name/description match the SKILL.md content. The workflow covers system decomposition, trust boundaries, STRIDE threats, mitigations, prioritization and tracking — all coherent with the stated purpose. No unrelated capabilities (cloud creds, CI tokens, etc.) are requested.
Instruction Scope
SKILL.md is a guidance document for running threat-model workshops and producing artifacts. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect secrets. Prompts and outputs are limited to threat-modeling artifacts and facilitation.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk writes and reduces supply-chain risk.
Credentials
No required environment variables, credentials, or config paths are declared. The guidance discusses assets and sensitive data conceptually but does not request or demand secrets or unrelated credentials.
Persistence & Privilege
always is false and model invocation is permitted (default). The skill does not request persistent presence or to modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install threat - 安装完成后，直接呼叫该 Skill 的名称或使用
/threat触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of the deep threat modeling workflow skill.
- Provides a structured, six-stage process covering scope, diagramming, STRIDE-style threats, mitigations, prioritization, and iteration.
- Includes practical tips, exit conditions, and a final review checklist for effective team-driven threat modeling.
- Designed for use during new feature design, architecture review, or responding to compliance and security requirements.
元数据
常见问题
Threat 是什么？
Deep threat modeling workflow—system decomposition, trust boundaries, STRIDE-style threats, mitigations, prioritization, and tracking. Use when designing new... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 123 次。
如何安装 Threat？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install threat」即可一键安装，无需额外配置。
Threat 是免费的吗？
是的，Threat 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Threat 支持哪些平台？
Threat 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Threat？
由 mike47512（@mike47512）开发并维护，当前版本 v1.0.0。
推荐 Skills