security 플러그인
Supply chain, secrets and access for a repository and its agents: action-owner allowlist, vulnerability scan and SBOM, provenance checks for skills and MCP servers, key rotation, access review, an inventory of admin entrances with multi-factor authentication, threat models, and vulnerability intake, with gate checks for secrets, action owners, and admin entrances, a pre-push hook for private terms, and a quarantine for third-party text.
security 플러그인 설치 방법
두 명령을 모두 Claude Code 안에서 실행하십시오. 첫 번째는 마켓플레이스를 한 번 추가하고, 두 번째는 플러그인을 설치합니다.
/plugin marketplace add uncovertechtalent/cto-powersuit
/plugin install security@cto-powersuitsecurity 구성 요소
플러그인 파일에서 읽어온 8개의 항목입니다.
Skills 8
작업이 일치하면 Claude가 로드합니다- access-review
Read-only review of who can change a GitHub repository and how: admins, collaborators and outside collaborators, deploy keys, token lists where the caller can see them, rulesets and their bypass actors, classic branch protection, every merge or push that went past a rule, such as a pull request merged with the admin bypass instead of the required review, and, for an organisation, whether it requires two-factor authentication and which members have it off. Never changes a setting. Use for a quarterly access review, before an audit, when someone leaves, or when a team wants to know whether its review rule holds. Activates on "/access-review", "who has access", "access review", "who can push to main", "were reviews bypassed", "admin merges", "list deploy keys", "does the org require 2FA", "members without 2FA".
- admin-entrances
List every place an administrator can sign in (cloud consoles and root accounts, identity provider and email admin, directory, VPN and remote access, source control and CI/CD owners, DNS and registrar, password manager, SaaS admin consoles, on-premises servers, device management, backups and logs, vendor access) and record for each one the owner, whether multi-factor authentication is enforced, the weakest method an admin can still use, and any exception with its reason, the person who accepted it and its end date. Writes docs/security/admin-entrances.md from a template and installs the gate check security.admin-entrances. Use for a security baseline, before an audit or a NIS2 or ISO 27001 assessment, when a cloud account, a domain or a VPN is added, and with each quarterly access review. Activates on "/admin-entrances", "admin entrances", "MFA inventory", "where is MFA missing", "is MFA on for admins", "multi-factor audit", "NIS2 21(2)(j)".
- private-terms
Keep private terms out of public repositories and pages: names of prospective employers or clients, internal shorthand, family names in business copy, private hosts and addresses. The term list stays on the owner's machine; a pre-push hook stops a push that adds a term, and a gate dry run scans the tree and the built pages. Use before a repository goes public, after a private note landed in a public file, or when an agent writes into public repositories. Activates on "/private-terms", "private terms", "keep this name out of the repo", "a private note went public", "block internal names", "pre-push check for names".
- quarantine
Keep third-party text away from coding agents that hold tools. Raw text from outside (a post, an email, a README, a web page, a chat paste) goes into a store outside every indexed folder, and an agent reads an item only as a fixed-shape summary from a local model that has no tools. A PreToolUse hook denies every other read of the store. Use when an agent works next to private data and can push, send or run commands, before it reads text from strangers, or after text from outside landed in a knowledge base. Activates on "/quarantine", "quarantine this", "save this post for later", "summarise this page safely", "untrusted text", "prompt injection", "keep this out of the vault".
- secrets
Keep secret values out of the repository and rotate the ones that got out: a pre-push hook that refuses a push whose new commits add a secret, a gate check for secret patterns and .env files in tracked files, a one-line scan for repositories without the gate, and a key-rotation runbook per secret that never prints the value. Use when a scan or a review finds a key in the repository, before a repository goes public, when someone with access leaves, on a rotation schedule, or to stop a key before it is pushed. Activates on "/secrets", "scan for secrets", "we committed a key", "rotate this key", "key rotation runbook", "is there a secret in this repo", "block secrets in CI", "pre-push secrets hook", "stop a key before the push".
- supply-chain
Secure what a repository runs that someone else wrote: actions pinned by commit SHA, an allowlist of action owners, update pull requests that keep the pins current, a vulnerability scan of the lock files, an SBOM, and a provenance check before anyone installs an agent skill or an MCP server. Use when a team adds a new action, dependency, skill or MCP server, before an audit or a customer questionnaire, or after news of a malicious package or repository campaign. Activates on "/supply-chain", "pin our actions", "is this MCP server safe", "can we install this skill", "check this repo before we install it", "scan our dependencies", "generate an SBOM", "supply chain security".
- threat-model
Write a short threat model for one RFC or one risky change: assets, entry points and trust boundaries, threats by category with likelihood and impact, mitigations with owners and tickets, and the residual risk someone accepts by name. Covers the threats of coding agents and their tools as entry points. Linked to the decisions/rfc skill: the RFC links the model, and the model feeds the RFC's risks section. Use when an RFC opens for comments, or when a change adds an entry point, a data class, a permission, a secret, or a third party. Activates on "/threat-model", "threat model this", "what could go wrong with this change", "security review of the RFC", "STRIDE".
- vuln-intake
Turn Dependabot alerts, security advisories and scan results into tickets with a fix-by date per severity: critical 7 days, high 30, medium 90, low 180 by default, from a policy page the team can change. Drafts each ticket in the format of the sdlc/ticket skill, skips findings that already have a ticket, and lists the ones past their date. Creates nothing without the user's go. Use after a scan, on a weekly intake, or when alerts pile up. Activates on "/vuln-intake", "triage our Dependabot alerts", "turn the alerts into tickets", "which vulnerabilities are overdue", "fix-by dates", "security backlog".
Claude Code에서 security 사용하기
Skills는 명령어가 필요하지 않습니다. 요청이 설명과 일치하면 Claude가 이를 읽습니다.
업데이트, 비활성화 또는 삭제
- 플러그인 업데이트 (shell)
- claude plugin update security@cto-powersuit
- marketplace 새로고침
- /plugin marketplace update cto-powersuit
- 일시적으로 비활성화
- /plugin disable security@cto-powersuit
- 삭제
- /plugin uninstall security@cto-powersuit
security의 스킬
- access-reviewuncovertechtalent/cto-powersuit
Read-only review of who can change a GitHub repository and how: admins, collaborators and outside collaborators, deploy keys, token lists where the caller can see them, rulesets and their bypass actors, classic branch protection, every merge or push that went past a rule, such as a pull request merged with the admin bypass instead of the required review, and, for an organisation, whether it requires two-factor authentication and which members have it off. Never changes a setting. Use for a quarterly access review, before an audit, when someone leaves, or when a team wants to know whether its review rule holds. Activates on "/access-review", "who has access", "access review", "who can push to main", "were reviews bypassed", "admin merges", "list deploy keys", "does the org require 2FA", "members without 2FA".
2개 파일8스타 - quarantineuncovertechtalent/cto-powersuit
Keep third-party text away from coding agents that hold tools. Raw text from outside (a post, an email, a README, a web page, a chat paste) goes into a store outside every indexed folder, and an agent reads an item only as a fixed-shape summary from a local model that has no tools. A PreToolUse hook denies every other read of the store. Use when an agent works next to private data and can push, send or run commands, before it reads text from strangers, or after text from outside landed in a knowledge base. Activates on "/quarantine", "quarantine this", "save this post for later", "summarise this page safely", "untrusted text", "prompt injection", "keep this out of the vault".
2개 파일8스타 - supply-chainuncovertechtalent/cto-powersuit
Secure what a repository runs that someone else wrote: actions pinned by commit SHA, an allowlist of action owners, update pull requests that keep the pins current, a vulnerability scan of the lock files, an SBOM, and a provenance check before anyone installs an agent skill or an MCP server. Use when a team adds a new action, dependency, skill or MCP server, before an audit or a customer questionnaire, or after news of a malicious package or repository campaign. Activates on "/supply-chain", "pin our actions", "is this MCP server safe", "can we install this skill", "check this repo before we install it", "scan our dependencies", "generate an SBOM", "supply chain security".
3개 파일8스타 - vuln-intakeuncovertechtalent/cto-powersuit
Turn Dependabot alerts, security advisories and scan results into tickets with a fix-by date per severity: critical 7 days, high 30, medium 90, low 180 by default, from a policy page the team can change. Drafts each ticket in the format of the sdlc/ticket skill, skips findings that already have a ticket, and lists the ones past their date. Creates nothing without the user's go. Use after a scan, on a weekly intake, or when alerts pile up. Activates on "/vuln-intake", "triage our Dependabot alerts", "turn the alerts into tickets", "which vulnerabilities are overdue", "fix-by dates", "security backlog".
2개 파일8스타 - admin-entrancesuncovertechtalent/cto-powersuit
List every place an administrator can sign in (cloud consoles and root accounts, identity provider and email admin, directory, VPN and remote access, source control and CI/CD owners, DNS and registrar, password manager, SaaS admin consoles, on-premises servers, device management, backups and logs, vendor access) and record for each one the owner, whether multi-factor authentication is enforced, the weakest method an admin can still use, and any exception with its reason, the person who accepted it and its end date. Writes docs/security/admin-entrances.md from a template and installs the gate check security.admin-entrances. Use for a security baseline, before an audit or a NIS2 or ISO 27001 assessment, when a cloud account, a domain or a VPN is added, and with each quarterly access review. Activates on "/admin-entrances", "admin entrances", "MFA inventory", "where is MFA missing", "is MFA on for admins", "multi-factor audit", "NIS2 21(2)(j)".
8스타 - private-termsuncovertechtalent/cto-powersuit
Keep private terms out of public repositories and pages: names of prospective employers or clients, internal shorthand, family names in business copy, private hosts and addresses. The term list stays on the owner's machine; a pre-push hook stops a push that adds a term, and a gate dry run scans the tree and the built pages. Use before a repository goes public, after a private note landed in a public file, or when an agent writes into public repositories. Activates on "/private-terms", "private terms", "keep this name out of the repo", "a private note went public", "block internal names", "pre-push check for names".
8스타 - secretsuncovertechtalent/cto-powersuit
Keep secret values out of the repository and rotate the ones that got out: a pre-push hook that refuses a push whose new commits add a secret, a gate check for secret patterns and .env files in tracked files, a one-line scan for repositories without the gate, and a key-rotation runbook per secret that never prints the value. Use when a scan or a review finds a key in the repository, before a repository goes public, when someone with access leaves, on a rotation schedule, or to stop a key before it is pushed. Activates on "/secrets", "scan for secrets", "we committed a key", "rotate this key", "key rotation runbook", "is there a secret in this repo", "block secrets in CI", "pre-push secrets hook", "stop a key before the push".
8스타 - threat-modeluncovertechtalent/cto-powersuit
Write a short threat model for one RFC or one risky change: assets, entry points and trust boundaries, threats by category with likelihood and impact, mitigations with owners and tickets, and the residual risk someone accepts by name. Covers the threats of coding agents and their tools as entry points. Linked to the decisions/rfc skill: the RFC links the model, and the model feeds the RFC's risks section. Use when an RFC opens for comments, or when a change adds an entry point, a data class, a permission, a secret, or a third party. Activates on "/threat-model", "threat model this", "what could go wrong with this change", "security review of the RFC", "STRIDE".
8스타
security 플러그인 질문
security 플러그인은 어떻게 설치하나요?
Claude Code에서 /plugin marketplace add uncovertechtalent/cto-powersuit를 실행한 다음 /plugin install security@cto-powersuit을 실행하십시오.
security 플러그인에는 무엇이 포함되나요?
security은(는) 8개 스킬을(를) 묶습니다.
security 플러그인을 어떻게 업데이트하거나 삭제하나요?
shell에서 claude plugin update security@cto-powersuit를 사용하여 업데이트하거나 /plugin의 Installed 탭에서 수행하세요. 삭제하려면 /plugin uninstall security@cto-powersuit을 사용하세요.
security 플러그인의 라이선스는 무엇인가요?
플러그인 manifest에 명시된 대로 MIT입니다.