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

mrhlaingbwardevPipes a download into a shellSkill

web3-security

mrhlaingbwardev/agentic-hacking-skills/skills/web3-security/SKILL.md

Use when user says "web3 စစ်", "contract စစ်", "defi ဖောက်", "solidity စစ်", "web3 hack", "smart contract vulnerability". Hunts million-dollar bugs in smart contracts - reentrancy, oracle manipulation, access control bypass, flashloan exploits. Writes working PoCs, chains exploits, maximizes impact. Zero theory - pure attack.

glowingkittyReads credentialsSkill

security-fix

glowingkitty/OpenMates/.claude/skills/security-fix/SKILL.md

Guarded dev-only security fix from a validated fix request (allowlisted fix classes, release-age selection, path guard, isolated CI, dev deploy). Started headlessly by scripts/security_monitor.py.

LeanmcpSkill

security-repro

Leanmcp/superview.sh/skills/security-repro/SKILL.md

Build safe, local, defensive reproductions of ALREADY-PATCHED, publicly disclosed security vulnerabilities (CVEs, vendor advisories, AI-agent incidents) for whitepapers, control testing, and education. Use this skill whenever the user wants to reproduce, demonstrate, or write up a known vulnerability or security incident — phrases like "reproduce this CVE", "build a repro for", "demonstrate the EchoLeak/Cursor/postmark-mcp issue", "show how this exploit worked", "add a reproducibility guide", or "pull the NVD/CVE details for". It fetches advisory metadata from NVD and CVE.org, confirms the issue is fixed, and produces a vulnerable-vs-patched harness that is offline, loopback-only, and uses synthetic markers. It NEVER discovers, develops, or weaponizes new zero-days and refuses any unpatched or live-target request.

nearaiReads credentialsSkill

security-review

nearai/ironclaw/skills/security-review/SKILL.md

Security audit for code changes and PRs — OWASP top 10, auth flows, data handling, secrets exposure, supply chain risks. Writes findings as actionable items.

Often used withlinkerd-patterns·dependency-cve-sweep·project-guidelines-example

h0rn3tDeletes or force-pushesSkill

go-security

h0rn3t/golang-skills/skills/go-security/SKILL.md

Use when writing or reviewing Go code that touches untrusted input, secrets, or credentials — SQL, shell, or template injection, path traversal, SSRF, cookies and security headers, password hashing, TLS settings, token comparison, or what may appear in a log line. Also use when a handler accepts a file name, URL, or command argument from a client, or when asked to find "vulnerabilities", even if the user never says "security". Does not cover the os.Root and crypto/rand mechanics (see go-defensive) or the dependency CVE scan in the gate (see go-linting).

drvossReads credentialsSkill

security-scan

drvoss/everything-copilot-cli/skills/security/security-scan/SKILL.md

Use when you want a quick security pass on code changes or dependencies — checks OWASP Top 10 patterns, runs dependency audits, and surfaces critical vulnerabilities with targeted fixes.

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

relaticleSkill

spatie-security

relaticle/relaticle/.claude/skills/spatie-security/SKILL.md

Apply Spatie's security guidelines when configuring applications, databases, servers, credentials, or signed Git commits, or when reviewing code for security concerns; use for SSL setup, CSRF protection, password hashing, database permissions, and server hardening.

mohitmishra786Skill

rust-security

mohitmishra786/low-level-dev-skills/skills/rust/rust-security/SKILL.md

Rust security skill for supply chain safety and memory-safe development. Use when auditing dependencies with cargo-audit, enforcing policies with cargo-deny, reviewing RUSTSEC advisories, writing memory-safe FFI patterns, or integrating fuzzing and Miri into a security review pipeline. Activates on queries about cargo-audit, cargo-deny, RUSTSEC advisories, supply chain security, Rust CVEs, safe FFI, or fuzzing for security.

wgpsecSkill

agent-security

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

AI Agent 系统安全测试方法论。当目标系统使用 AI Agent 执行工具调用、多 Agent 协作、 或自主决策时触发。覆盖 OWASP Agentic AI Security Top 10 (ASI01-ASI10): 目标劫持、工具滥用、身份权限、供应链、代码执行、记忆投毒、多 Agent 通信、 级联故障、人机信任利用、失控 Agent。

theopencoSkill

security-audit

theopenco/llmgateway/.agents/skills/security-audit/SKILL.md

Security best practices, vulnerability review, and full security audits for LLM Gateway. Use when writing security-sensitive code (auth, sessions, API keys, provider keys, billing, webhooks, user-supplied URLs, admin routes, CORS, rendering user content), when asked for a security review, security report, vulnerability research, pen test, or security audit, and for the monthly audit routine that fixes confirmed findings in a PR.

Often used withcreate-stories·community-led-growth·story-done

jefflesterReads credentialsSkill

api-security

jefflester/claude-skills-supercharged/.claude/skills/api-security/SKILL.md

API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifying APIs.

Often used withbinary-diff·pentest-tools·llm-security

loulanyueDeletes or force-pushesSkill

perl-security

loulanyue/awesome-claude-notes/skills/perl-security/SKILL.md

Comprehensive Perl security covering taint mode, input validation, safe process execution, DBI parameterized queries, web security (XSS/SQLi/CSRF), and perlcritic security policies.

Often used withpytorch-patterns·architecture-decision-records

gyuhaSkill

fg-security

gyuha/forge/skills/fg-security/SKILL.md

Domain-specialised security audit of a codebase, outside the forge loop — a vendored multi-phase methodology (recon → parallel attack-class hunting → independent validation → machine-readable findings) whose findings, past a severity gate and your approval, become fix-forward backlog plans. Artefacts stay OUTSIDE the repo (upstream's ~/security-audit-skill/) so a vulnerability list has no path into a commit at all. Always skipped in fg-next all / fg-loop. Use in contexts like 'forge security', 'fg-security', '보안 감사', '취약점 찾아줘', 'security audit'.

simoncorrySkill

security-scan

simoncorry/foundry/.agents/skills/security-scan/SKILL.md

Single-round adversarial security scan.

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

z91772524-aiSkill

api-security

z91772524-ai/pojia-next-mac/skills/api-security/SKILL.md

API security testing for REST/GraphQL/WebSocket/SOAP: discovery, authz, BOLA/IDOR, JWT/OAuth, rate-limit, and CI-oriented validation workflows.

Often used withbinary-diff·pentest-tools·llm-security

z91772524-aiSkill

llm-security

z91772524-ai/pojia-next-mac/skills/llm-security/SKILL.md

LLM/agent security testing: prompt injection, tool abuse, data exfil paths, guardrail bypass research, and evaluation harnesses.

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

KbWenSkill

auth-security

KbWen/agentic-os/.agents/skills/auth-security/SKILL.md

Secure authentication and authorization when credentials, sessions, roles, or permissions change.

PydanticSkill

review-security

pydantic/monty/.agents/skills/review-security/SKILL.md

Security review of the current branch against its merge base — sandbox escapes, memory errors, panics and resource-limit bypasses. Use when reviewing changes for security risk, or before merging anything touching the heap/ module, path_security.rs, the wire protocol or the pool.

Often used withreview-bugbot·split-to-prs·create-rule

chaenmasahiro0425Reads credentialsSkill

security-scan

chaenmasahiro0425/claude-security-scan/SKILL.md

開発者のPC・手元のgitリポジトリ・GitHub・Vercelと公開サイト・クラウド（AWS / Google Cloud / Azure / Cloudflare / Supabase）・Gmailを読み取り専用で横断スキャンし、重要度別のHTMLレポートと前回からの差分を出すスキル。「セキュリティチェックして」「セキュリティスキャン」「脆弱性ないか見て」「APIキー漏れてない？」「乗っ取られてないか確認」「新しく出たリスクだけ教えて」「毎週スキャンを設定して」等で使う。設定の変更・送信・削除はしない。直すときは1件ずつ利用者の承認を取る。

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

xrplevmSkill

security-audit

xrplevm/node/.claude/skills/security-audit/SKILL.md

Run a full security audit across all focus areas in parallel, reporting findings to peersyst/security

Often used withcreate-stories·community-led-growth·story-done