securitythreat-model

mgreenly 的头像作者 mgreenly

威胁建模安全技能

📖 中文导读:威胁建模安全技能 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。

name: security/threat-model description: Threat Modeling security skill

Threat Modeling

Identify attack surface, enumerate threats, prioritize mitigations before writing code.

Process for Planned Work

1. Identify assets:

  • What are we protecting? (API keys, conversation history, user data)
  • What would attacker want? (credentials, code execution, data exfil)

2. Enumerate entry points:

  • User input (terminal, config, environment)
  • Network (LLM API responses)
  • Filesystem (config files, database)

3. Apply STRIDE per entry point:

  • Spoofing: Can attacker impersonate?
  • Tampering: Can attacker modify data?
  • Repudiation: Can actions be denied?
  • Information disclosure: Can secrets leak?
  • Denial of service: Can availability be impacted?
  • Elevation of privilege: Can attacker gain capabilities?

4. Prioritize:

  • Likelihood × Impact = Risk
  • Address high-risk items first
  • Document accepted risks

For new features ask:

  • What new entry points does this create?
  • What can go wrong if input is malicious?
  • What's the blast radius if this component is compromised?