Search Results for "claude code"

The claude-code-security-review repository implements a GitHub Action that uses Claude (via the Anthropic API) to perform semantic security audits of code changes in pull requests. Rather than relying purely on pattern matching or static analysis, this action feeds diffs and surrounding context to Claude to reason about potential vulnerabilities (e.g. injection, misconfigurations, secrets exposure, etc).

Claude-BugHunter is a Claude Code skill bundle focused on bug hunting, security testing, and external red-team research workflows. It packages a large collection of specialized skills, slash commands, and disclosed-report patterns so Claude Code can reason through common vulnerability classes more systematically. The project is meant to help authorized testers structure reconnaissance, triage, hypothesis building, exploitation reasoning, and reporting. ...

Defending Code Reference Harness is a reference implementation for autonomous vulnerability discovery and remediation with Claude. It is designed for security teams that want a structured way to test, triage, and patch software issues with agent support. The project includes skills for threat modeling, scanning, triage, patching, and customizable autonomous analysis workflows.

...The platform also examines plugins, skills, hooks, package installs, and agent configurations before they are trusted. It integrates with major coding agents including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and GitHub Copilot CLI. Local operation requires no cloud account, while optional cloud services add synchronized evidence, shared policies, fleet visibility, and team approvals.

...It wraps an existing AI coding agent with orchestration for reconnaissance, exploit exploration, validation, and reporting. The project can work through a browser War Room or CLI while relying on agents such as Claude Code, Codex, Hermes, or locally hosted models. It emphasizes reproducible benchmark claims, keyless operation, and a clear status table that separates stable capabilities from experimental or roadmap work. Its stated target areas include web apps, CTF challenges, source-code review, OSS vulnerability hunting, smart contracts, and embedded or robotics research. ...

SkillSpector is a security scanner built to evaluate AI agent skills before they are installed or trusted. It helps teams inspect skills used by tools such as Claude Code, Codex CLI, and Gemini CLI. The project focuses on detecting vulnerabilities, malicious behavior, and risky patterns that may be hidden inside skill files. It combines fast static checks with optional LLM-based semantic review for issues that require deeper intent analysis. It supports several input types, including Git repositories, URLs, zip files, folders, and individual files. ...

...The package checks locally available tools and can bootstrap supporting scripts, MCP servers, and utilities when needed. Scope gates, case initialization, timelines, evidence chains, reports, and field journals encourage repeatable and auditable work. It supports clients such as Claude Code, Codex CLI, Cursor, and Cline across Windows, Linux, macOS, and Kali Linux. The repository also preserves reusable lessons so later investigations can avoid previously documented mistakes.