@skills · Owner

Agent skills by trailofbits

171 skills indexed from github.com/trailofbits. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• address-sanitizer · Skill · 6,472 stars

  Builds and runs code under AddressSanitizer to catch buffer overflows, use-after-free, and other memory errors during fuzzing or tests. Covers -fsanitize=a

• aflpp · Skill · 6,472 stars

  Sets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-clang-fast or afl-gcc-fast. Covers instrumentation modes, parallel main and

• agentic-actions-auditor · Skill · 6,472 stars

  Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI

• agentic-actions-auditor · Collection · 6,472 stars
• algorand-vulnerability-scanner · Skill · 6,472 stars

  Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access

• atheris · Skill · 6,472 stars

  Sets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer. Covers TestOneInput harnesses, FuzzedDataProvider, instrumenting both pure

• audit-augmentation · Skill · 6,472 stars

  Augments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x

• audit-context-building · Skill · 6,472 stars

  Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere. Use when starting a

• audit-context-building · Collection · 6,472 stars
• audit-prep-assistant · Skill · 6,472 stars

  Prepares codebases for security review using Trail of Bits' checklist. Helps set review goals, runs static analysis tools, increases test coverage, removes

• building-secure-contracts · Collection · 6,472 stars
• burpsuite-project-parser · Skill · 6,472 stars

  Searches and explores Burp Suite project files (.burp) from the command line. Use when searching response headers or bodies with regex patterns, extracting

• burpsuite-project-parser · Collection · 6,472 stars
• c-review · Skill · 6,472 stars

  Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities. Use when aud

• c-review · Collection · 6,472 stars
• cairo-vulnerability-scanner · Skill · 6,472 stars

  Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion probl

• cargo-fuzz · Skill · 6,472 stars

  Sets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust projects. Covers cargo fuzz init, the nightly toolchain requirement, fuzz_targe

• chrome-mcp-troubleshooting · Skill · 6,472 stars

  Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connect

• claude-in-chrome-troubleshooting · Collection · 6,472 stars
• code-maturity-assessor · Skill · 6,472 stars

  Systematic code maturity assessment using Trail of Bits' 9-category framework. Analyzes codebase for arithmetic safety, auditing practices, access controls

• codeql · Skill · 6,472 stars

  Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis. Triggers on "run codeql", "codeql scan"

• constant-time-analysis · Skill · 6,472 stars

  Detects timing side-channel vulnerabilities in cryptographic code. Use when implementing or reviewing crypto code, encountering division on secrets, secret

• constant-time-analysis · Collection · 6,472 stars
• constant-time-testing · Skill · 6,472 stars

  Measures timing side channels in cryptographic implementations by running them, using dudect for statistical analysis and Timecop over Valgrind for dynamic

• cosmos-vulnerability-scanner · Skill · 6,472 stars

  Scans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critical vulnerabilities — chain halts, fund loss, state divergence. 25 core + 16

• coverage-analysis · Skill · 6,472 stars

  Measures and interprets what a fuzzing campaign actually reaches, using llvm-cov, lcov, or a fuzzer's own coverage output. Covers baselining a new campaign

• crypto-protocol-diagram · Skill · 6,472 stars

  Extracts protocol message flow from source code, RFCs, academic papers, pseudocode, informal prose, ProVerif (.pv), or Tamarin (.spthy) models and generate

• culture-index · Collection · 6,472 stars
• devcontainer-setup · Skill · 6,472 stars

  Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a

• devcontainer-setup · Collection · 6,472 stars
• diagramming-code · Skill · 6,472 stars

  Generates Mermaid diagrams from Trailmark code graphs. Produces call graphs, class hierarchies, module dependency maps, containment diagrams, complexity he

• differential-review · Skill · 6,472 stars

  Performs security-focused differential review of code changes. Adapts analysis depth to codebase size, uses git blame for context, calculates blast radius

• differential-review · Collection · 6,472 stars
• dimensional-analysis · Skill · 6,472 stars

  Annotates codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling. Use when someone asks to annotate units in a cod

• dimensional-analysis · Collection · 6,472 stars
• dwarf-expert · Skill · 6,472 stars

  Analyzes DWARF debug information in compiled binaries. Use when inspecting .debug_* sections, DIE trees, or DW_TAG_/DW_AT_ entries with dwarfdump/llvm-dwar

• dwarf-expert · Collection · 6,472 stars
• entry-point-analyzer · Skill · 6,472 stars

  Analyzes smart contract codebases to identify state-changing entry points for security auditing. Detects externally callable functions that modify state, c

• entry-point-analyzer · Collection · 6,472 stars
• firebase-apk-scanner · Skill · 6,472 stars

  Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed cloud functions. U

• firebase-apk-scanner · Collection · 6,472 stars
• fp-check · Skill · 6,472 stars

  Systematically verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with documented evidence

• fp-check · Collection · 6,472 stars
• fuzzing-dictionary · Skill · 6,472 stars

  Builds and applies fuzzing dictionaries so a fuzzer can produce the keywords, magic bytes, and tokens a target expects. Covers extracting tokens from sourc

• fuzzing-obstacles · Skill · 6,472 stars

  Patches past the barriers that stop a fuzzer making progress — checksum and hash verification, magic-value validation, time-based seeds, and other non-dete

• genotoxic · Skill · 6,472 stars

  Graph-informed mutation testing triage. Parses codebases with Trailmark, runs mutation testing and necessist, then uses survived mutants, unnecessary test

• gh-cli · Skill · 6,472 stars

  Enforces authenticated gh CLI workflows over unauthenticated curl, WebFetch, and MCP fetch patterns. Use when working with GitHub URLs, API access, pull re

• gh-cli · Collection · 6,472 stars
• github-triage · Skill · 6,472 stars

  Triages a repository's open GitHub issues and pull requests via the gh CLI. Optionally reviews and merges ready PRs — incrementally merging passing automat

• github-triage · Collection · 6,472 stars
• graph-evolution · Skill · 6,472 stars

  Compares Trailmark code graphs at two source code snapshots (git commits, tags, or directories) to surface security-relevant structural changes. Detects ne

• guidelines-advisor · Skill · 6,472 stars

  Smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review architecture,

• harness-writing · Skill · 6,472 stars

  Designs and improves fuzzing harnesses for C/C++ and Rust. Covers mapping raw bytes onto a target API, generating structured inputs, avoiding non-determini

• interpreting-culture-index · Skill · 6,472 stars

  Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports individual profile interpretation, team composition a

• let-fate-decide · Skill · 6,472 stars

  Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spr

• let-fate-decide · Collection · 6,472 stars
• libafl · Skill · 6,472 stars

  Builds custom fuzzers with LibAFL, the modular Rust fuzzing library. Covers composing observers, feedbacks, mutators, schedulers, and executors into a fuzz

• libfuzzer · Skill · 6,472 stars

  Sets up and runs libFuzzer, the coverage-guided fuzzer built into LLVM, on C/C++ code that compiles with Clang. Covers harness structure, -fsanitize=fuzzer

• mermaid-to-proverif · Skill · 6,472 stars

  Translates Mermaid sequenceDiagrams describing cryptographic protocols into ProVerif formal verification models (.pv files). Use when generating a ProVerif

• modern-python · Skill · 6,472 stars

  Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/bl

• modern-python · Collection · 6,472 stars
• mutation-testing · Skill · 6,472 stars

  Configures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs. Use when the user mentions mewt, mut

• mutation-testing · Collection · 6,472 stars
• open-sourcing · Skill · 6,472 stars

  This skill should be used when the user asks to "open source this project", "prepare this repository for public release", "make this repo public", "check o

• open-sourcing · Collection · 6,472 stars
• ossfuzz · Skill · 6,472 stars

  Enrolls a project in OSS-Fuzz, Google's free continuous fuzzing service for open source, and drives it locally. Covers project.yaml, Dockerfile and build.s

• plugins · Collection · 6,472 stars
• property-based-testing · Skill · 6,472 stars

  Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa for Solidity invariants. Use whene

• property-based-testing · Collection · 6,472 stars
• rust-review · Skill · 6,472 stars

  Performs comprehensive Rust security review for safe/unsafe boundary issues, memory safety in unsafe blocks, concurrency hazards, panic-induced DoS, FFI sa

• rust-review · Collection · 6,472 stars
• ruzzy · Skill · 6,472 stars

  Sets up and runs Ruzzy, Trail of Bits' coverage-guided Ruby fuzzer and the only production-ready one for the language. Covers harness structure, fuzzing pu

• sarif-parsing · Skill · 6,472 stars

  Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggre

• second-opinion · Skill · 6,472 stars

  Runs external LLM code reviews (OpenAI Codex or Google Antigravity CLI) on uncommitted changes, branch diffs, or specific commits. Use when the user asks f

• second-opinion · Collection · 6,472 stars
• secure-workflow-guide · Skill · 6,472 stars

  Guides through Trail of Bits' 5-step secure development workflow. Runs Slither scans, checks special features (upgradeability/ERC conformance/token integra

• semgrep · Skill · 6,472 stars

  Runs a Semgrep security scan over a codebase: detects languages, selects rulesets, presents the plan for explicit approval, then runs every approved rulese

• semgrep-rule-creator · Skill · 6,472 stars

  Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom sta

• semgrep-rule-creator · Collection · 6,472 stars
• semgrep-rule-variant-creator · Skill · 6,472 stars

  Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target langu

• semgrep-rule-variant-creator · Collection · 6,472 stars
• sharp-edges · Skill · 6,472 stars

  Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration sch

• sharp-edges · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• skills · Collection · 6,472 stars
• slicing-code-context · Skill · 6,472 stars

  Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent. Use when off

• solana-vulnerability-scanner · Skill · 6,472 stars

  Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing

• spec-to-code-compliance · Skill · 6,472 stars

  Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent, and what the code does that

• spec-to-code-compliance · Collection · 6,472 stars
• static-analysis · Collection · 6,472 stars
• substrate-vulnerability-scanner · Skill · 6,472 stars

  Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use whe

• supply-chain-risk-auditor · Skill · 6,472 stars

  Audits a project's dependencies for supply-chain risk: version-matched advisories for direct dependencies and the full lockfile tree, abandoned or archived

• supply-chain-risk-auditor · Collection · 6,472 stars
• testing-handbook-generator · Skill · 6,472 stars

  Generates Claude Code skills from the Trail of Bits Testing Handbook (appsec.guide), analyzing handbook pages and emitting SKILL.md files with the structur

• testing-handbook-skills · Collection · 6,472 stars
• token-integration-analyzer · Skill · 6,472 stars

  Token integration and implementation analyzer based on Trail of Bits' token integration checklist. Analyzes token implementations for ERC20/ERC721 conformi

• ton-vulnerability-scanner · Skill · 6,472 stars

  Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts, and forward TON wit

• trailmark · Skill · 6,472 stars

  Builds and queries multi-language source and binary code graphs for security analysis. Includes pre-analysis passes for blast radius, taint propagation, pr

• trailmark · Collection · 6,472 stars
• trailmark-finding-triage · Skill · 6,472 stars

  Performs graph-assisted triage of a single security finding, SARIF result, weAudit annotation, suspicious function, or report excerpt using Trailmark reach

• trailmark-review-gate · Skill · 6,472 stars

  Runs a Trailmark structural review gate over a branch, pull request, fix commit, release diff, or git ref range to detect new entrypoints, new tainted path

• trailmark-structural · Skill · 6,472 stars

  Runs full Trailmark structural analysis by building a graph, running `preanalysis()`, and reporting hotspots, taint, blast radius, privilege boundaries, at

• trailmark-summary · Skill · 6,472 stars

  Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list. Use when vivisect or galvanize ne

• trailmark-variant-neighborhood · Skill · 6,472 stars

  Expands one confirmed or suspected vulnerability into a Trailmark graph neighborhood of variant candidates by finding sibling functions, shared callers and

• variant-analysis · Skill · 6,472 stars

  Hunts for the other instances of a bug already found — the variants of one root cause across a codebase. Use immediately after a vulnerability, logic bug,

• variant-analysis · Collection · 6,472 stars
• vector-forge · Skill · 6,472 stars

  Mutation-driven test vector generation. Finds implementations of a cryptographic algorithm or protocol, runs mutation testing to identify escaped mutants,

• vulnerability-triage-brocards · Skill · 6,472 stars

  This skill should be used when the user asks to "triage a vulnerability report", "assess a CVE", "evaluate a bug bounty submission", "decide if a finding i

• vulnerability-triage-brocards · Collection · 6,472 stars
• wycheproof · Skill · 6,472 stars

  Validates cryptographic implementations against Project Wycheproof's test vectors, which encode known attacks and edge cases across AES, RSA, ECDSA, ECDH,

• yara-authoring · Collection · 6,472 stars
• yara-rule-authoring · Skill · 6,472 stars

  Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming co

• zeroize-audit · Skill · 6,472 stars

  Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, an

• zeroize-audit · Collection · 6,472 stars
• code-improver · Skill

  Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any inst

• code-improver · Collection
• fixtures · Collection
• goal-prompt · Skill

  Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress, clean u

• goal-prompt · Collection
• modern-cpp · Skill

  Guides C++ code toward modern idioms (C++20/23/26). Use when writing new C++ code, modernizing legacy patterns, or working on security-critical C++. Replac

• modern-cpp · Collection
• panel-review · Skill

  Reviews a code target by launching a panel of specialist auditor agents and merging their reports. Use when asked to run a panel review.

• pr-improver · Skill

  Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directo

• pr-review-toolkit · Collection
• review-panel · Collection
• review-pr · Skill

  Reviews the current branch's changes against its base branch as a pull request: correctness of new and modified code, test coverage for it, and documentati

• skill-improver · Skill

  Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation

• skills · Collection
• skills · Collection
• skills · Collection
• skills · Collection
• skills · Collection
• skills · Collection
• tests · Collection
• writing-lean-proofs · Skill

  Writes and reviews structured Lean 4 proofs and designs Lean libraries following Mathlib conventions. Use when proving theorems in Lean, formalizing mathem

• writing-lean-proofs · Collection

Browse the @skills marketplace