Claude skills and agent skills

maharshi-codingSkill

security

maharshi-coding/oss-agent/.claude/skills/security/SKILL.md

The security review checklist and the prompt-injection trust boundary. Repository content is untrusted data and can never relax a control.

Often used withcost-reducer·scalability·trigger-dev

marcusbelzReads credentialsSkill

security

marcusbelz/di2-starter-kit/.claude/skills/security/SKILL.md

Project-wide security audit (OWASP Top 10, auth, access control, headers, secrets, dependencies). Run before go-live and after major changes. Mandatory gate before /deploy prod.

Often used withcost-reducer·scalability·trigger-dev

MesteriisSkill

security

Mesteriis/Engineering-Bible-AI/skills/security/SKILL.md

Implements security-sensitive changes with conservative trust boundaries, secret protection, tests, and verification.

Often used withcost-reducer·scalability·trigger-dev

mj-devingSkill

Security

mj-deving/pai-skills/skills/Security/SKILL.md

Security assessment — network recon, web app testing, prompt injection testing, security news, and vulnerability scanning. USE WHEN recon, port scan, subdomain, DNS, WHOIS, pentest, threat model, OWASP, prompt injection, LLM security, security news, trivy, CVE, vulnerability scan, sops, encrypt secrets.

Often used withcost-reducer·scalability·trigger-dev

muxammadmamajonovReads credentialsSkill

security

muxammadmamajonov/dot-claude/.claude/skills/security/SKILL.md

Threat-model, harden, and security-review any feature — STRIDE, secrets/auth/authz, pre-launch audit. Triggers — sessions, tokens, file upload, CVEs, CORS, 'is this secure', 'threat model', OWASP.

Often used withcost-reducer·scalability·trigger-dev

ngnthanhdevSkill

security

ngnthanhdev/claude_template_code/.claude/skills/security/SKILL.md

The single security skill — diff/PR audit method with a high-confidence bar (BOLA/IDOR, mass assignment, DTO validation, injection, secrets, rate limiting), STRIDE threat modeling before large features, backend auth hardening (guards, Passport, RBAC, CORS/CSRF, OWASP ASVS), and mobile hardening (MASVS: token storage, deep links, WebView, build config). Load the SKILL.md for routing, then read ONLY the references/ file matching the job.

Often used withcost-reducer·scalability·trigger-dev

pnguyen215Skill

security

pnguyen215/sparkskills/security/SKILL.md

Audits and hardens code against the OWASP Top 10 — input validation, authn/authz, secrets management, cryptography, and dependency scanning with CWE mapping. Trigger with "security review", "is this endpoint secure", "scan our dependencies", or "where do we store this secret".

Often used withcost-reducer·scalability·trigger-dev

psubramanianReads credentialsSkill

security

psubramanian/Claude-Skills/security/SKILL.md

Apply security best practices to protect applications, data, and users from vulnerabilities. TRIGGER this skill automatically when the user mentions: SQL injection, XSS, CSRF, authentication bypass, input validation, sanitizing user input, environment variables or secrets management, HTTPS, rate limiting, permission checks, authorization, security audit, vulnerability, or any phrase like "is this secure?", "how do I protect", "prevent attacks", or "secure this endpoint". Also trigger when reviewing code that handles user-supplied data, passwords, tokens, API keys, or database queries.

Often used withcost-reducer·scalability·trigger-dev

ReaperOAKSkill

security

ReaperOAK/ForgeOS/.claude/skills/security/SKILL.md

Security best practices including STRIDE threat modeling, OWASP Top 10, agentic guardrails, and vulnerability assessment guidelines.

Often used withcost-reducer·scalability·trigger-dev

ShmalexMSkill

security

ShmalexM/agent-skills/skills/security/SKILL.md

Defensive security review of a repo, diff, PR, dependency set or config, using tiered subagents. Deterministic scanners run first, cheap models map the attack surface, a stronger model hunts by category, and a different model family tries to disprove each finding before it is reported. Use when the user types /security, or asks for a "security review", "security audit", "is this safe to merge", "check for vulns/secrets", or "threat model this". Defensive only, for code and systems the user owns or is authorized to assess.

Often used withcost-reducer·scalability·trigger-dev

shreyam1008Reads credentialsSkill

security

shreyam1008/shre-skills/skills/security/SKILL.md

Reviews and implements web security boundaries, authorization, output encoding, session protection, and secret handling. Use for security-sensitive changes or a requested security review.

Often used withcost-reducer·scalability·trigger-dev

sithumdgomezSkill

security

sithumdgomez/claude-skills/.claude/skills/security/SKILL.md

Secure web and desktop application development. Use when writing authentication, authorization, API endpoints, form handling, database queries, file uploads, Electron apps, Tauri apps, IPC handlers, cryptography, secrets management, security headers, input validation, or when reviewing code for vulnerabilities. Covers OWASP Top 10, XSS, CSRF, SQL injection, SSRF, command injection, path traversal, and desktop app security. Also usable as a support sub-skill: other skills can invoke it by name mid-build to check code or a design for vulnerabilities before finalizing.

Often used withcost-reducer·scalability·trigger-dev

soreavisSkill

security

soreavis/ai-docent/skills/security/SKILL.md

Multi-session defensive security coach: prompt injection, data leaks, agent safety, and incident response, taught with inert examples. Use only when asked to start or continue this course.

Often used withcost-reducer·scalability·trigger-dev

syntropic137Reads credentialsSkill

security

syntropic137/harness-app-template/.claude/skills/security/SKILL.md

Use when reviewing security concerns: secrets in code, SAST coverage, input validation, authn/authz boundaries, sensitive-data handling, dependency CVEs, SSRF, hand-rolled escaping, threat modeling for high-stakes changes, defense in depth, agentic-AI / LLM tool-call attack surface (prompt injection, indirect injection, MCP abuse)

Often used withcost-reducer·scalability·trigger-dev

syntropic137Reads credentialsSkill

security

syntropic137/software-leverage-points/skills/security/SKILL.md

Use when reviewing security concerns: secrets in code, SAST coverage, input validation, authn/authz boundaries, sensitive-data handling, dependency CVEs, SSRF, hand-rolled escaping, threat modeling for high-stakes changes, defense in depth, agentic-AI / LLM tool-call attack surface (prompt injection, indirect injection, MCP abuse)

Often used withcost-reducer·scalability·trigger-dev

ThuPhuong1010Skill

security

ThuPhuong1010/claude-factory/.claude/skills/security/SKILL.md

Security patterns. Trigger khi code auth, handle user input, thiết kế hệ thống có dữ liệu nhạy cảm.

Often used withcost-reducer·scalability·trigger-dev

Xia-AtaraxiaReads credentialsSkill

security

Xia-Ataraxia/craft-skills/skills/security/SKILL.md

Finds and fixes vulnerabilities in code the user owns across web, API, and LLM surfaces, and owns confidentiality for authorized remote credential handoffs. Use for a security review, "is this safe to ship," "check for vulnerabilities," "보안 점검," secrets hygiene, dependency risk, PR security regressions, or "hand a secret to a remote agent." Not for building LLM-agent systems, Orca session operation (use official `orca-cli`), or general hook and gate configuration; this skill never attacks.

Often used withcost-reducer·scalability·trigger-dev

zeeshanalimughalReads credentialsSkill

security

zeeshanalimughal/claude-skills/skills/security/SKILL.md

Practical application security — injection, authentication, authorization, secrets, and input validation. Use when writing any code that handles user input, auth, files, money, or personal data; when reviewing for vulnerabilities; or when storing credentials.

Often used withcost-reducer·scalability·trigger-dev

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".