agentsclimarketplace

SOC Copilot

Skill G4rb3n/SOC-Copilot

SOC子引擎,基于agent-skills技术通过AI赋能SOC平台,对SOC告警进行研判、调查、响应。

Install
npx -y skills add G4rb3n/SOC-Copilot

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

SOC子引擎,基于agent-skills技术通过AI赋能SOC平台,对SOC告警进行研判、调查、响应。SOC子引擎的核心理念为构建一个自我学习的安全引擎,可预测的告警通过规则匹配并通过脚本自动化处置,不可预测的告警通过大模型研判分析,分析完后生成规则和处置脚本,用户审核后固化到规则引擎,除此之外,用户可以主动输入SKILL对SOC子引擎进行训练。

SKILL.md

1.9 KB, as published. Nobody here has run it

工作流程

1、从用户输入的路径获取该目录下的所有告警日志,通过经验'{reference/triage/triage.md}'对告警进行研判分析。若匹配到了已有规则'{scripts/triage_rules/}'则直接跳到下面调查环境,若未匹配到规则,则研判完成后按照模板'{assets/triage_rule.yml}'生成对应的研判规则(规则要尽可能地泛化),生成后询问用户是否手工编辑修改或反馈模型修改,最终用户审核后固化到'{scripts/triage_rules}'。 2、询问用户是否需要进一步分析或溯源,若需要,则调用'{reference/investigation/investigation.md}'对告警进行调查分析。调查溯源完毕后,生成对应的python调查脚本,生成后询问用户是否手工编辑修改或反馈模型修改,最终用户审核后固化到'{scripts/investigation}' 3、询问用户是否进行响应处置,若需要,则调用'{reference/incident_response/incident_response.md}'对失陷主机进行响应处置。响应处置完毕后,生成对应的bash/powershell响应脚本,生成后询问用户是否手工编辑修改或反馈模型修改,最终用户审核后固化到'{scripts/incident_response}'。 4、如果该告警日志的研判结论为定向攻击,则根据模板'{assets/analysis_report.md}'输出分析报告保存到'{reports/}'路径。

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.