skills
Security auditing skills for code review, fuzzing, and vulnerability triage
All Skills in This Repository (91)
Pure Emerald Level Indicatorsdwarf-expert
Explain DWARF debug information and DIE trees from compiled binaries.
ask-questions-if-underspecified
Identify underspecified requests and generate clarifying questions before implementation.
interpreting-culture-index
Interpret Culture Index profiles from PDF or JSON inputs into structured CI insights.
audit-context-building
Build a line-by-line mental model of codebases for security audits.
claude-in-chrome-troubleshooting
Diagnose and fix Claude MCP Chrome extension connectivity issues.
entry-point-analyzer
Identify and classify state-changing entry points in smart contracts.
semgrep-rule-creator
Create Semgrep rules with test-first validation and structured metadata.
constant-time-analysis
Detect timing side-channel vulnerabilities in cryptographic code and output CI-ready JSON results.
property-based-testing
Design property-based test strategies and review workflows across multiple languages.
differential-review
Analyze security-focused git diffs and generate markdown audit reports.
insecure-defaults
Detect insecure default configurations with hardcoded secrets and weak authentication.
yara-rule-authoring
Validate YARA-X rule syntax, metadata, and atom quality with linting.
Frequently Asked Questions
FAQPage SchemaHow to install Trail of Bits skills?โผ
Run `npx skills add trailofbits/skills --all -g -y` in your terminal to install the full security skill suite globally.
What security tasks can these skills automate?โผ
They cover C/C++ and Rust security review, smart contract auditing, Semgrep and CodeQL scanning, mutation testing, supply-chain risk audits, and vulnerability triage with false-positive verification.
Do these skills work with Claude Code and Codex?โผ
Yes. The repository is a Claude Code plugin marketplace, and Codex loads it directly through its Claude marketplace compatibility with no extra configuration.
Can AI agents find real vulnerabilities with these skills?โผ
Yes. The suite includes measured, multi-agent pipelines like c-review and zeroize-audit that verify coverage against parsed source and require compiler-level evidence before confirming findings.
Do I need security expertise to use these skills?โผ
No. Each skill encodes the expert methodology, evidence requirements, and common rationalizations to reject, so your agent applies senior-auditor discipline from plain-English requests.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core