trailofbits/skills

这个仓库里有 83 个技能，GitHub 星标 ★ 7,113。

• agentic-actions-auditorAudits GitHub Actions workflows for security vulnerabilities in AI agent integra
• audit-context-buildingUnderstand a codebase before looking for bugs in it - what each function assumes
• algorand-vulnerability-scannerScans Algorand smart contracts for 11 common vulnerabilities including rekeying
• audit-prep-assistantPrepares codebases for security review using Trail of Bits' checklist. Helps set
• cairo-vulnerability-scannerScans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including fe
• code-maturity-assessorSystematic code maturity assessment using Trail of Bits' 9-category framework. A
• cosmos-vulnerability-scannerScans Cosmos SDK blockchain modules and CosmWasm contracts for consensus-critica
• guidelines-advisorSmart contract development advisor based on Trail of Bits' best practices. Analy
• secure-workflow-guideGuides through Trail of Bits' 5-step secure development workflow. Runs Slither s
• solana-vulnerability-scannerScans Solana programs for 6 critical vulnerabilities including arbitrary CPI, im
• substrate-vulnerability-scannerScans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithm
• token-integration-analyzerToken integration and implementation analyzer based on Trail of Bits' token inte
• ton-vulnerability-scannerScans TON (The Open Network) smart contracts for 3 critical vulnerabilities incl
• burpsuite-project-parserSearches and explores Burp Suite project files (.burp) from the command line. Us
• c-reviewPerforms comprehensive C/C++ security review for memory corruption, integer over
• chrome-mcp-troubleshootingDiagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mc
• code-improverRuns an autonomous review-and-fix improvement loop over any code target — a skil
• pr-improverRuns an autonomous review-and-fix improvement loop over the current branch's cha
• skill-improverRuns an autonomous review-and-fix improvement loop over a Claude Code skill unti
• constant-time-analysisDetects timing side-channel vulnerabilities in cryptographic code. Use when impl
• interpreting-culture-indexInterprets Culture Index (CI) surveys, behavioral profiles, and personality asse
• devcontainer-setupCreates devcontainers with Claude Code, language-specific tooling (Python/Node/R
• differential-reviewPerforms security-focused differential review of code changes. Adapts analysis d
• dimensional-analysisAnnotates codebases with dimensional analysis comments documenting units, dimens
• dwarf-expertAnalyzes DWARF debug information in compiled binaries. Use when inspecting .debu
• entry-point-analyzerAnalyzes smart contract codebases to identify state-changing entry points for se
• firebase-apk-scannerScans Android APKs for Firebase security misconfigurations including open databa
• fp-checkSystematically verifies suspected security bugs to eliminate false positives, pr
• gh-cliEnforces authenticated gh CLI workflows over unauthenticated curl, WebFetch, and
• github-triageTriages a repository's open GitHub issues and pull requests via the gh CLI. Opti
• goal-promptDrafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. U
• let-fate-decideDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning w
• modern-cppGuides C++ code toward modern idioms (C++20/23/26). Use when writing new C++ cod
• modern-pythonConfigures Python projects with modern tooling (uv, ruff, ty). Use when creating
• mutation-testingConfigures mewt or muton campaigns, analyzes surviving mutants, and investigates
• open-sourcingThis skill should be used when the user asks to "open source this project", "pre
• post-patch-validation>
• property-based-testingWrites, reviews, and debugs property-based tests — Hypothesis, fast-check, propt
• review-walkthroughGenerates an interactive HTML walkthrough for reviewing code changes. Use only w
• rust-reviewPerforms comprehensive Rust security review for safe/unsafe boundary issues, mem
• second-opinionGets independent code reviews from Codex or Antigravity for uncommitted changes,
• semgrep-rule-creatorCreates custom Semgrep rules for detecting security vulnerabilities, bug pattern
• semgrep-rule-variant-creatorCreates language variants of existing Semgrep rules. Use when porting a Semgrep
• sharp-edgesIdentifies error-prone APIs, dangerous configurations, and footgun designs that
• spec-to-code-complianceCheck code against the documentation that specifies it - which requirements hold
• codeql>-
• sarif-parsing>-
• semgrep>-
• supply-chain-risk-auditorAudits a project's dependencies for supply-chain risk: version-matched advisorie
• address-sanitizerBuilds and runs code under AddressSanitizer to catch buffer overflows, use-after
• aflppSets up and runs AFL++ for multi-core fuzzing of C/C++ projects built with afl-c
• atherisSets up and runs Atheris, the coverage-guided Python fuzzer built on libFuzzer.
• cargo-fuzzSets up and runs cargo-fuzz, the standard fuzzing tool for Cargo-based Rust proj
• constant-time-testingMeasures timing side channels in cryptographic implementations by running them,
• coverage-analysisMeasures and interprets what a fuzzing campaign actually reaches, using llvm-cov
• fuzzing-dictionaryBuilds and applies fuzzing dictionaries so a fuzzer can produce the keywords, ma
• fuzzing-obstaclesPatches past the barriers that stop a fuzzer making progress — checksum and hash
• harness-writingDesigns and improves fuzzing harnesses for C/C++ and Rust. Covers mapping raw by
• libaflBuilds custom fuzzers with LibAFL, the modular Rust fuzzing library. Covers comp
• libfuzzerSets up and runs libFuzzer, the coverage-guided fuzzer built into LLVM, on C/C++
• ossfuzzEnrolls a project in OSS-Fuzz, Google's free continuous fuzzing service for open
• ruzzySets up and runs Ruzzy, Trail of Bits' coverage-guided Ruby fuzzer and the only
• testing-handbook-generatorGenerates Claude Code skills from the Trail of Bits Testing Handbook (appsec.gui
• wycheproofValidates cryptographic implementations against Project Wycheproof's test vector
• audit-augmentation>
• crypto-protocol-diagramExtracts protocol message flow from source code, RFCs, academic papers, pseudoco
• diagramming-code>
• genotoxicGraph-informed mutation testing triage. Parses codebases with Trailmark, runs mu
• graph-evolution>
• mermaid-to-proverifTranslates Mermaid sequenceDiagrams describing cryptographic protocols into ProV
• slicing-code-contextSelects bounded, graph-informed source slices with Trailmark and delegates focus
• trailmarkBuilds and queries multi-language source and binary code graphs for security ana
• trailmark-finding-triagePerforms graph-assisted triage of a single security finding, SARIF result, weAud
• trailmark-review-gateRuns a Trailmark structural review gate over a branch, pull request, fix commit,
• trailmark-structuralRuns full Trailmark structural analysis by building a graph, running `preanalysi
• trailmark-summaryRuns a Trailmark summary analysis on a codebase. Returns auto-detected languages
• trailmark-variant-neighborhoodExpands one confirmed or suspected vulnerability into a Trailmark graph neighbor
• vector-forgeMutation-driven test vector generation. Finds implementations of a cryptographic
• variant-analysisHunts for the other instances of a bug already found — the variants of one root
• vulnerability-triage-brocards>-
• writing-lean-proofsWrites and reviews structured Lean 4 proofs and designs Lean libraries following
• yara-rule-authoring>
• zeroize-auditDetects missing zeroization of sensitive data in source code and identifies zero