Development · Secure coding

Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs.

microsoft/onnxruntime

Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

ruvnet/ruflo

Reviews code or recent changes for bugs, security issues, performance problems and maintainability, reporting findings by severity with the reason and a fix.

pretend1111/claude-desktop-app

Checks a codebase for hardcoded secrets, vulnerable dependencies, weak input handling, weak authentication and unsafe transport settings before deployment or merge.

TheDecipherist/claude-code-mastery

Applies safer package manager defaults and dependency vetting to JavaScript and TypeScript projects to reduce supply-chain attack risk.

bodadotsh/npm-security-best-practices

Gives the agent a five-step review routine that reads the full file first, labels each finding as bug, security, performance, style or suggestion, and ends with a summary.

FareedKhan-dev/claude-code-from-scratch

Reviews WordPress plugin, theme and block code after an agent writes or edits it, catching missing escaping, nonces, capability checks and unprepared queries.

amElnagdy/guard-skills

Reviews APIs, configuration schemas and library interfaces for footguns, the designs where the easy path leads to insecure use, using a four-phase analysis.

trailofbits/skills

Finds sensitive data that C, C++ or Rust code never wipes from memory, including wipes the compiler optimizes away, using source, assembly and control-flow analysis.

trailofbits/skills

Reviews AdvPL and TLPP source against SonarQube rules, ProtheusDOC requirements, security, performance and Protheus conventions, and reports findings by severity.

totvs/engpro-advpl-tlpp-skills

Plans a change to the NGINX Ingress Controller before any code: acceptance criteria, security impact, affected layers, invariants, test surface and an ordered file list.

nginx/kubernetes-ingress

Runs untrusted or AI-generated code in isolated Deno Sandbox microVMs using the @deno/sandbox SDK, with lifecycle, process and streaming guidance.

denoland/skills

Plans and builds full-stack features with frontend, backend and security handled together, including a written design and a security checklist before any code.

Jeffallan/claude-skills

Develops WordPress themes, plugins, Gutenberg blocks and WooCommerce features with nonce, escaping and capability checks, phpcs linting and caching tuned for speed.

Jeffallan/claude-skills

Steers C++ code toward C++20, C++23 and C++26 idioms such as smart pointers, concepts, std::expected and std::print, with a security focus.

trailofbits/skills

A ten-category security checklist for the agent-core codebase, to run before any security-sensitive change or pull request: secrets, input validation, SQL, access control and prompt injection.

openJiuwen-ai/agent-core

Automated code review and security linting integration for CI/CD pipelines using reviewdog.

AgentSecOps/SecOpsAgentKit

Expert in secure backend coding practices specializing in input validation, authentication, and API security.

aiskillstore/marketplace

Apply security-conscious thinking when generating or modifying code.

techygarg/lattice

Configure and audit security review capabilities as one layer in a defense-in-depth pull-request program.

jeremylongshore/tons-of-skills-marketplace

Reviews a design or change for security before it ships — authentication and authorization, data handling, secrets, dependencies, and the secure-development practices around it.

cbrock84/headcount

Perform adversarial Python security code reviews grounded in the OpenSSF Secure Coding Guide for Python.

SpecterOps/skills

Use webhint in .NET repositories that ship browser-facing frontends.

managedcode/dotnet-skills