Find the best CLAUDE.md, AGENTS.md and Claude skills

BuilderIOSkill

security

BuilderIO/agent-native/.agents/skills/security/SKILL.md

Secure app data, actions, routes, and external input. Use when changing authentication, authorization, database access, uploads, untrusted content, or server-side requests to user-provided URLs.

Often used withcost-reducer·albert-dm·scalability

parcadeiSkill

security

parcadei/Continuous-Claude/.claude/skills/security/SKILL.md

Security audit workflow - vulnerability scan → verification

Often used withcost-reducer·albert-dm·scalability

gridacoSkill

security

gridaco/grida/.agents/skills/security/SKILL.md

How to handle `GRIDA-SEC-<id>` security boundaries in the Grida repo. Triggers when you encounter a `GRIDA-SEC` tag in source/docs, when modifying files under any tagged path, or when adding a new prevented- vulnerability record. Each `GRIDA-SEC-<id>` identifies a structural trust boundary documented in `/SECURITY.md`. This skill explains the contract, mandates a security review before committing changes to any tagged file, and shows how to register a new id. Use whenever "GRIDA-SEC" appears in context.

Often used withcost-reducer·albert-dm·scalability

static-web-serverReads credentialsSkill

security

static-web-server/static-web-server/.agents/skills/security/SKILL.md

Review or implement security-sensitive code in the Static Web Server (SWS) project — path traversal defenses, symlink and hidden-file policy, TLS, security headers, CORS, basic auth, untrusted input parsing, and vulnerability handling. Use when touching fs/path.rs, static_files/security.rs, cors.rs, basic_auth.rs, tls.rs, security_headers.rs, redirects/rewrites, directory listing download, or any code that handles request paths or headers.

Often used withcost-reducer·albert-dm·scalability

BankrBotSkill

Security

BankrBot/skills/ethskills-security/SKILL.md

Solidity vulnerabilities, defensive code patterns, and a pre-deployment audit checklist. Covers reentrancy, oracle manipulation, token decimals, SafeERC20, ERC-4626 inflation, infinite approvals, and MEV.

Often used withcost-reducer·albert-dm·scalability

zhaoxuya520Skill

api-security

zhaoxuya520/reverse-skill-private/skills/api-security/SKILL.md

Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication, authorization, rate-limit, and CI/CD testing.

Often used withattack-chain·llm-security·pentest-tools

zhaoxuya520Skill

llm-security

zhaoxuya520/reverse-skill-private/skills/llm-security/SKILL.md

Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Often used withattack-chain·pentest-tools·binary-diff

OpenAISkill

security-scan

openai/codex-security/plugins/codex-security/skills/security-scan/SKILL.md

Use for a standard, single-pass security audit of an entire repository or a scoped path, package, folder, or submodule with no diff to review. This is the default repository scan. Do not use for PR, commit, branch, or working-tree diffs, or for deep, multi-pass scans.

Often used withdjango-security·deployment-patterns·postgres-patterns

withkynamSkill

vc-security

withkynam/vibecode-pro-max-kit/.claude/skills/vc-security/SKILL.md

STRIDE + OWASP-based security audit with optional auto-fix. Scans code for vulnerabilities, categorizes by severity, and can iteratively fix findings using vc-autoresearch pattern.

OpenAISkill

security-scan

openai/plugins/plugins/codex-security/skills/security-scan/SKILL.md

Use for a standard, single-pass security audit of an entire repository or a scoped path, package, folder, or submodule with no diff to review. This is the default repository scan. Do not use for PR, commit, branch, or working-tree diffs, or for deep, multi-pass scans.

Often used withdjango-security·deployment-patterns·postgres-patterns

odooSkill

odoo-security

odoo/odoo/skills/odoo-security/SKILL.md

Security audit of Odoo addon code: access control (ir.access, field groups, sudo), injection (SQL, domain, eval, XSS via Markup/markup()), untrusted public methods/RPC, controller auth/CSRF, file access, deserialization, returning complex objects, getattr/setattr, timing attacks. Use when auditing an addon, or judging whether a specific construct (a sudo, raw SQL, a route, ...) is safe.

SentrySkill

sentry-security

getsentry/sentry/.agents/skills/sentry-security/SKILL.md

Sentry-specific security review based on real vulnerability history. Use when reviewing Sentry endpoints, serializers, or views for security issues. Trigger keywords: "sentry security review", "check for IDOR", "access control review", "org scoping", "cross-org", "security audit endpoint".

AWSSkill

aws-security

aws/agent-toolkit-for-aws/plugins/aws-core/skills/aws-security/SKILL.md

AWS security service suitability, coverage and cost recommendations: WAF/origin overlap, AWS Network Firewall inspection coverage and policy review, VPC endpoint, Transit Gateway/Cloud WAN segmentation and DNS Firewall security-control suitability, certificate renewal ownership and monitoring, incident response triage ownership, centralized security log store (CloudWatch or Security Lake). Also factual configuration, findings, data sources and severity scoring for GuardDuty, Inspector, Security Hub V2/OCSF (Exposure, connectors, automation), Security Hub CSPM/ASFF (standards, controls), Macie, Detective, Security Lake, AWS Security Incident Response membership and case coverage, and Organizations security policies. Applies to advisory security-service choices even when one service is named. Implementation, rule or code authoring, deployment, scans and troubleshooting outside these factual procedures belong to specialist skills. Supports local AWS CLI and AWS MCP.

zakirkunSkill

security-ops

zakirkun/deep-eye/.agents/skills/security-ops/SKILL.md

Router for Deep Eye agent skills: pentest, bug-bounty, red-team, blue-team, ctf. Use for security ops, mixed intent, offensive vs defensive choice.

tinyfish-ioSkill

dep-security

tinyfish-io/tinyfish-cookbook/skills/dep-security/SKILL.md

Check every dependency in a package.json against live CVE databases and security advisories in real time — specifically targeting vulnerabilities disclosed in the last 48 hours, the window that Snyk, Dependabot, and npm audit miss. Use this skill whenever a user mentions checking dependencies for vulnerabilities, wants to audit their package.json, asks about CVEs for their packages, says "are my dependencies safe", "check my packages for security issues", "any new vulnerabilities in my deps", or pastes a package.json and asks about security. Also trigger when a user mentions wanting fresher data than Snyk or Dependabot provides. Returns: which dependencies have brand-new vulnerabilities, severity, what the vulnerability does, whether a patched version exists yet, and a prioritised fix list.

No other project uses it yet

zereightReads credentialsSkill

security-scan

zereight/gitlab-mcp/.github/skills/security-scan/SKILL.md

Rapid security scanning workflow for code changes. Activates a focused security sweep. Activate when: security scan, scan for vulnerabilities, check for secrets, security check, run security audit, check deps.

Often used withdjango-security·deployment-patterns·postgres-patterns

wgpsecSkill

mcp-security

wgpsec/AboutSecurity/skills/ai-security/mcp-security/SKILL.md

MCP (Model Context Protocol) 协议安全测试方法论。当目标环境使用 MCP Server 集成外部工具、 需要评估 MCP 工具描述安全性、或测试 Agent 通过 MCP 调用工具时的安全边界时触发。 覆盖: 工具描述投毒、地毯式骗局(动态篡改)、指令覆盖(Shadow Tool)、隐藏指令(ANSI/Unicode)、 跨 Server 攻击、Token 窃取、Schema 操纵、上下文溢出。

first-flukeSkill

oma-security

first-fluke/oh-my-ag/.agents/skills/oma-security/SKILL.md

Scan application source, agent skills, and MCP components; run penetration tests against scoped web test deployments, validate findings, and configure scan gates. Use oma-qa for broad quality reviews and domain skills for remediation.

first-flukeSkill

oma-security

first-fluke/oh-my-ag/skills/oma-security/SKILL.md

Scan application source, agent skills, and MCP components; run

heartleoSkill

security-scan

heartleo/zlib/.agents/skills/security-scan/SKILL.md

Scan zlib for security problems before a release or after a dependency, network, credential, or file-handling change — govulncheck, secret scanning, GitHub alert review, and a credential-boundary code review — and handle a private vulnerability report through a GitHub security advisory.

Often used withdjango-security·deployment-patterns·postgres-patterns