skills - Trail of Bits Claude Code skills for security rese

项目说明

Trail of Bits Skills Marketplace

A Claude Code plugin marketplace from Trail of Bits pro skills to enhance AI-assisted security analysis, testing, and de workflows. Codex can load this marketplace through its Claude marketplace compatibility.

> Also see: claude-code-config · codex-config · skills-curated · claude-code-de · dropkit · coop

Installation

Claude Code Marketplace

Browse and Install Plugins

Codex

Codex supports Claude plugin marketplaces directly, so this repository does not need Codex-specific sidecar metadata.

Install the marketplace with:

ChatGPT Workspace Marketplace

Use this repository's .claude-plugin/marketplace.json for workspace imports.
Skills that include agents/openai.yaml also need interface.display_name and
interface.short_description in that YAML file; plugin metadata does not supply them.
After a metadata fix is published, sync the repository again in your workspace
marketplace to retry failed imports.

Local De

To add the marketplace locally (e.g., for testing or de), na to the parent directory of this repository:

A Plugins

Smart Contract Security

| Plugin | Description |
|--------|-------------|
| building-secure-contracts | Smart contract security toolkit with scanners for 6 blockchains and 5 de guideline assistants |
| entry-point-analyzer | Identify state-changing entry points in smart contracts for security auditing |

Code Auditing

| Plugin | Description |
|--------|-------------|
| agentic-actions-auditor | Audit GitHub Actions workflows for AI agent security |
| audit-context-building | Understand a codebase before looking for bugs in it, one function at a time |
| burpsuite-project-parser | Search and extract data from Burp Suite project files |
| c-review | Comprehensive C/C++ security code review, with co against a parse of the source |
| differential-review | Security-focused differential review of code changes with git history analysis |
| dimensional-analysis | Annotate codebases with dimensional analysis comments to detect unit mismatches and formula bugs |
| fp-check | Systematic false positi for security bug analysis with mandatory gate reviews |
| insecure-defaults | Parallel audit workflow for fail-open insecure defaults, with a refuting per candidate file |
| rust-review | Comprehensive Rust security review co safe/unsafe boundary, memory safety, concurrency, panic-DoS, FFI, and async runtime with SARIF output |
| semgrep-rule-creator | Create and refine Semgrep rules for custom detection |
| semgrep-rule- | Port existing Semgrep rules to new target languages with test-dri |
| sharp-edges | Identify error-prone APIs, dangerous configurations, and footgun designs |
| static-analysis | Static analysis toolkit with CodeQL, Semgrep, and SARIF parsing |
| supply-chain-risk-auditor | Audit npm, PyPI, and Go dependencies for ad, abandoned upstreams, publisher concentration, and install scripts |
| testing-handbook-skills | Skills from the Testing Handbook: fuzzers, static analysis, sanitizers, co |
| trailmark | Code graph analysis, bounded subagent context slicing, Mermaid diagrams, mutation testing triage, and protocol |
| | Find similar across codebases using pattern-based analysis |
| cards | Triage reports using 7 brocards to accept, dismiss, or request more info before deeper analysis |

Malware Analysis

| Plugin | Description |
|--------|-------------|
| yara-authoring | YARA detection rule authoring with linting, atom analysis, and best practices |

| Plugin | Description |
|--------|-------------|
| constant-time-analysis | Detect compiler-induced timing side-channels in cryptographic code |
| mutation-testing | Configure mutation testing, analyze sur mutants, and in bugs in weakly tested code |
| post-patch- | Help patch authors find missed and regressions, with reproducible failures and explicit gaps |
| property-based-testing | Write, review, and triage property-based tests — Hypothesis, fast-check, proptest, and Echidna or Medusa for Solidity in |
| spec-to-code-compliance | Check code against the documentation that specifies it, across contracts, C/C++, services, and firmware |
| writing-lean-proofs | Write structured Lean 4 proofs and design Lean libraries following Mathlib con |
| zeroize-audit | Detect missing or compiler-eliminated zeroization of secrets in C/C++ and Rust |

Reverse Engineering

| Plugin | Description |
|--------|-------------|
| dwarf-expert | Analyze DWARF debug info: parse and search DIEs, integrity, write DWARF parsing code |

Mobile Security

| Plugin | Description |
|--------|-------------|
| firebase-apk-scanner | Scan Android APKs for Firebase security misconfigurations |

De

| Plugin | Description |
|--------|-------------|
| code-improver | Autonomous re workflow o, plugins, or a branch, with a pluggable re, findings ledger, escalation, and scope guard |
| de | Create pre-configured de with Claude Code and language-specific tooling |
| gh-cli | Intercept GitHub URL fetches — WebFetch, MCP fetch tools, and curl/wget — and redirect to the authenticated gh CLI |
| git-cleanup | Safely clean up git worktrees and local branches: a dynamic workflow gathers merge e and tries to refute its own delete recommendations, behind gated confirmation |
| goal-prompt | Draft /goal commands for goal mode in Claude Code and Codex — completion conditions formatted to a copy-ready single line |
| github-triage | Triage open GitHub issues and PRs: merge ready bot/approved PRs, review unre ones , close resol with cited comments, cross-link pending fixes, and score the rest with local-only priority and change-size estimates |
| let-fate-decide | Draw Tarot cards using cryptographic randomness to add entropy to vague planning |
| modern-cpp | Modern C++ best practices (C++20/23/26) with compiler hardening and safe idioms |
| modern-python | Modern Python tooling and best practices with uv, ruff, and pytest |
| open-sourcing | Prepare a repository for public release: secrets hygiene, licensing, CI readiness, and release automation |
| re | Generate an interacti of branch changes with ordered diffs, explanations, and anchored review findings |
| second-opinion | Get independent reviews from Codex or Antigravity for uncommitted changes, branch diffs, and commits |

Team Management

| Plugin | Description |
|--------|-------------|
| culture-index | Interpret Culture Index sur for indi and teams |

Tooling

| Plugin | Description |
|--------|-------------|
| claude-in-chrome-troubleshooting | Diagnose and fix Claude in Chrome MCP extension connectivity issues |

Trophy Case

Bugs discovered using Trail of Bits Skills. Found something? Let us know!

When reporting bugs you', feel free to mention:
> Found using Trail of Bits Skills

| Skill | Bug |
|-------|-----|
| constant-time-analysis | Timing side-channel in ML-DSA signing |

Contributing

We welcome contributions! See AGENTS.md for skill authoring guidelines, and
run make check before you push — it runs most of CI locally (see AGENTS.md for
what it does not cover).

License

This work is licensed under a Creati Attribution-ShareAlike 4.0 International License. Made by Trail of Bits.

项目信息

开发语言：Python

Star 数：7372

技术要点

该项目属于漏洞知识库方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Trail of Bits Claude Code skills for security research, vulnerability detection, and audit workflows展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。