MoonshotAI
精选
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它围绕人工决策设计，结合应用自身上下文判断依赖风险的可达性与爆炸半径，并且明确不提供漏洞利用方法，适合安全评审场景。
适合谁使用
- 评估依赖告警的开发者
- 负责漏洞研判的安全工程师
- 需要理解依赖风险的技术管理者
- 使用技能自动化辅助依赖审查的团队
典型使用场景
- 针对具体应用上下文研判扫描器或安全公告发现
- 决定依赖风险应升级、延期、缓解还是进一步调查
- 向工程经理清晰解释风险与残余风险
- 规划采用大版本升级还是补丁级修复
项目优势
- 不仅看 CVSS 分数，还会结合应用上下文判断可达性和爆炸半径
- 支持多种生态系统和语言选项，并可调整决策深度
- 交付一页式风险卡片，包含暴露面、严重性、修复路径、决策、残余风险和测试计划
- 刻意不包含漏洞利用配方，更适合安全汇报和决策
使用前须知
- 它是对已有扫描器或安全公告结果进行研判，而不是主动发现新漏洞
- 不适合用于盲目合并所有机器人提交，也不用于编写攻击 PoC
- 主要目标不是完整编写 GHSA，因此更深度的漏洞库编辑不在范围内
README 快速开始
Dependency Risk Brief
Dependency upgrade risk card: CVSS/severity, exposure, blast radius, upgrade-vs-defer.
中文简介： 依赖升级风险简报（CVSS、暴露面、升或缓）。 — 详见 README.zh.md.
What this skill does
- Triages scanner/advisory findings for your app context
- Judges reachability and blast radius
- Recommends upgrade, defer (with date), or mitigate
- Never includes exploit recipes
Install
npx skills add / --skill dependency-risk-brief
Local monorepo: skills/dependency-risk-brief/.
Options
| Option | Values | Default |
|---|---|---|
lang | en · zh · bilingual | en |
ecosystem | npm · pip · go · maven · cargo · other · multi | multi |
decision | upgrade · defer · mitigate · investigate · auto | auto |
depth | lite · standard · strict | standard |
When to use
| Use | Don't |
|---|---|
| Human decision on a dependency alert | Blind auto-merge all bots |
| Explain risk to eng manager | Write attack PoCs |
| Plan major-bump vs patch | Full GHSA authoring as main goal |
Deliverable
One-page risk card: exposure, severity, fix path, decision, residual risk, test plan.
See SKILL.md.
Example
../../output/samples/dependency-risk-brief-example-01.md
License
MIT — see LICENSE.
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
xuchonglang
精选
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
精选
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.