스킬 찾기

Diagnose Claude in Chrome connection failures on macOS by checking native messaging hosts, the processes linking Chrome to Claude, and their settings. It guides fixes for competing configurations, stale wrappers, and session conflicts, including restart steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate a browser extension connection error
• Restore browser integration after a Claude Code update
• Switch browser automation between Claude Code and Cowork

Write and review YARA-X rules, which identify malware through file patterns. Refine detection strings and conditions, check rule quality with included scripts, test against clean files, improve performance, and migrate rules from legacy YARA.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Write rules targeting a specific malware family
• Review false positives and slow detection rules
• Migrate existing YARA rules to YARA-X

Set up Atheris to test Python code and C extensions with automatically varied inputs. It guides test harness creation, coverage tracking to explore more code, and AddressSanitizer setup for finding memory errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fuzzing a Python package or parser
• Investigating memory corruption in Python C extensions
• Turning raw bytes into typed test arguments

Compare code structure across two commits, tags, or directories to identify security-relevant changes. Produces a report on new attack paths, privilege boundaries, complexity, and how widely a change could affect other functions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare code structure before a release
• Investigate new attack paths after code changes
• Track untrusted data flows across a refactor

Get a quick structural overview of a codebase with Trailmark. The skill identifies programming languages, counts entry points where execution begins, and returns dependency information to support orientation before deeper analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting oriented in an unfamiliar codebase
• Checking languages and entry point counts before analysis
• Preparing a structural overview for Vivisect or Galvanize

Evaluate vulnerability reports using seven practical criteria, including attacker capabilities, real usage, documented behavior, and remediation costs. Produce a reasoned decision to accept, dismiss, or request more evidence before committing to deeper investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening AI-generated security findings before human review
• Assessing whether a reported CVE warrants investigation
• Reviewing bug bounty submissions

Measure which code fuzzing reaches as it tries many generated inputs. Use coverage reports to find unreachable areas, compare progress, and guide improvements to test harnesses, starting inputs, or dictionaries of useful input values.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Establish initial coverage for a fuzzing run
• Investigate why fuzzing stops reaching new code
• Compare coverage before and after harness changes

Builds and improves C/C++ and Rust fuzzing harnesses, the entry points that feed generated test data into code. Helps structure inputs, reach more code paths, and address crashes caused by inconsistent test behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing a first fuzzing harness
• Building structured inputs for an API
• Investigating crashes that cannot be reproduced

Connect static analysis results and human audit notes to a Trailmark code graph. Group findings by severity and compare them with input flow, impact, and privilege boundaries to prioritize investigation and understand findings in their code context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting Semgrep or CodeQL results to code structure
• Combining human audit notes with automated findings
• Prioritizing findings using input flow and impact

Create Mermaid diagrams from code relationships parsed by Trailmark. Visualize function calls, class inheritance, module dependencies, class members, complexity hotspots, and paths from inputs to sensitive functions, with adjustable focus, depth, and layout.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping function calls around a selected function
• Visualizing class inheritance and members
• Drawing module dependency maps

Assess a single suspected security issue using Trailmark's graph of code relationships. Gather evidence about reachable paths, input flow, and potential impact, then receive a priority verdict and a list of remaining manual checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritizing a static analysis finding before proof-of-concept work
• Checking whether entry points can reach a suspicious function
• Preparing code evidence for exploit validation

Compares code relationships before and after a branch, pull request, or release change using Trailmark. Flags structural security regressions, such as removed authorization checks or newly reachable sensitive operations, and provides evidence for reviewers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking structural security changes before merging a PR
• Reviewing call paths after a security fix
• Assessing attack surface changes in a release

Build a graph of functions and calls across multiple programming languages to investigate entry points, paths to sensitive operations, and potential impact. Use the results to prioritize security reviews and connect external findings with source code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing call paths from entry points to sensitive functions
• Prioritizing code for a security audit
• Connecting calls across language and RPC boundaries

Find other occurrences of a known bug across a codebase by tracing its root cause. Gradually broaden search patterns, assess matching candidates, assign severity, and document findings with rules to help prevent recurrence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding similar issues after discovering a vulnerability
• Building CodeQL or Semgrep queries from a known bug
• Checking whether similar code shares the same root cause

Set up libFuzzer to test C/C++ code with varied inputs guided by which code paths run. Build test harnesses, manage sample inputs and dictionaries, enable error detectors, and reproduce crashes or investigate stalled coverage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting fuzz testing for a C/C++ library
• Writing or debugging an LLVMFuzzerTestOneInput harness
• Investigating runs that find no crashes or new code paths

Helps set up and run cargo-fuzz for Rust projects using Cargo. Guides fuzz testing, which tries varied inputs, from writing test harnesses to detecting memory errors, reproducing crashes, and checking which code was exercised.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding fuzz tests to a Rust crate
• Generating structured test inputs
• Testing unsafe blocks or foreign-function calls

Create dictionaries of keywords and identifying byte sequences for fuzzing, or testing with generated inputs. Extract useful entries from code, binaries, or specifications, then configure fuzzers to explore parsing paths beyond initial input validation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a dictionary for JSON or XML parser fuzzing
• Add protocol keywords to generated test inputs
• Test image parsers with file signatures and chunk names

Identify checks and changing global state that block fuzzing, then adjust them in fuzzing builds. The skill covers targeted validation bypasses, repeatable behavior, coverage comparisons, and checks for false crash reports introduced by patches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Getting past checksum or hash checks during fuzzing
• Making time-seeded random behavior repeatable
• Comparing code coverage before and after a patch

Turn Trail of Bits Testing Handbook content into Claude Code skills for security testing. Creates or refreshes SKILL.md files using templates for tools, fuzzers, techniques, and subject areas, then validates structure and links between skills.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate security testing skills from handbook sections
• Refresh a skill after handbook updates
• Create multiple skills from handbook content

Checks cryptographic code against known attacks and edge cases using Project Wycheproof test vectors, predefined inputs and expected results. Helps load cases, interpret failures, compare implementations, and integrate checks into automated testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing cryptographic code against known attacks
• Comparing results across cryptographic libraries
• Investigating rejected or incorrectly accepted signatures

Turn a Mermaid sequence diagram of a cryptographic protocol into a ProVerif model, a file for formal security checks. It includes queries for secrecy, authentication, replay resistance, and forward secrecy where applicable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting a cryptographic protocol diagram into a .pv file
• Preparing session key secrecy checks
• Modeling authentication and replay resistance

Turn cryptographic code or specifications into sequence diagrams showing who sends each message, which cryptographic operations occur, and where failures stop the exchange. Outputs include Mermaid source, a plain text diagram, and a protocol summary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Visualizing handshake and key exchange steps
• Extracting message flows from RFCs and papers
• Diagramming ProVerif or Tamarin models

Select relevant code using Trailmark's map of function relationships, then delegate explanation, review, or edit proposals to a smaller model. Limit the supplied source, check cited evidence, and verify proposed changes before applying them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Asking a small model to explain a function
• Tracing callers and paths from entrypoints
• Requesting edit proposals for a specific line range

Audit C/C++ and Rust code for secrets left in memory. It checks missing or incomplete wipes, examines compiler output for removed cleanup operations, and produces reports with evidence and suggested fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing cryptographic key cleanup
• Checking password and token memory wipes
• Investigating cleanup removed by compiler optimization