테스트·보안 스킬

Review software before release by checking features, documentation, tests, code quality, and security. Use the Centinela QA agent to produce a versioned assessment with a release decision and specific reasons for any blockers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check readiness before a production release
• Run final checks before tagging a version
• Review documentation and technical debt

Review a codebase for unused code, outdated or vulnerable dependencies, and patterns that make maintenance harder. Produce a prioritized Markdown report, compare recurring findings with earlier scans, and prepare a handoff for the development agent.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run a periodic code quality review
• Check outstanding issues before a release
• Review code after a large refactoring

Review code for security issues in authentication, access controls, data handling, embedded secrets, and dependencies. The Centinela QA agent produces a report with severity ratings, an approval verdict, and recommended repair priorities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review security before a release
• Audit authentication or data-handling changes
• Run periodic codebase security reviews

Review and strengthen Go code against injection attacks, unsafe file access, authentication flaws, and secret exposure. Traces how untrusted data reaches sensitive operations, ranks findings by severity, and guides fixes, static analysis, and security testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a Go pull request for security issues
• Auditing a codebase and prioritizing vulnerabilities
• Checking user input, file access, and network requests

Write, review, audit, and debug Go tests that check observable behavior. Covers named test cases, integration test isolation, concurrent execution, race and goroutine leak detection, and finding causes of intermittent failures or gaps in test coverage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding tests for edge cases and error paths
• Reviewing test changes in a pull request
• Auditing unit and integration test isolation

Set up golangci-lint to check Go code for potential problems. Helps select checks, configure project rules, understand warnings, apply available automatic fixes, and document justified exceptions when a warning needs to be suppressed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up code checks for a Go project
• Understanding and fixing lint warnings
• Adding checks gradually to an existing codebase

Write and review Go tests using stretchr/testify. Choose assertions that continue or stop on failure, create mocks that verify expected calls, and organize related tests with shared setup and cleanup routines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing between assert and require
• Creating mocks and verifying expected calls
• Sharing setup and cleanup across related tests

Check whether an implementation or generated output meets its stated goal. Review files, required content, logical consistency, and project conventions, then receive PASS, WARN, or FAIL results with specific issues to fix.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Get a second opinion on an agent's completed work
• Check required fields in SKILL.md or configuration files
• Find placeholders and contradictions before sharing output

Review a coding agent’s work against its assigned requirements, permitted file changes, and verification evidence. Return a structured verdict with supporting reasons, identifying incomplete work, scope violations, or missing proof without modifying the reviewed files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a coding agent’s submitted work
• Checking changes against permitted file paths
• Identifying missing verification evidence

Evaluate a CCB execution round using task requirements, coordinator summaries, worker and checker reports, and command or test evidence. Produce a machine-readable decision distinguishing success, limited repair, partial completion, replanning, and blockers requiring intervention.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluating a round from coordinator and worker reports
• Deciding whether a limited repair is sufficient
• Recording partial success across independent branches

Review one task result returned by a CCB worker agent against its assigned scope, acceptance criteria, and expected verification. Identify hidden fallback behavior, reduced quality or scope, and missing evidence, then report the outcome and required rework.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a worker agent's completed task
• Checking results against acceptance criteria
• Finding unreported scope reductions or missing evidence

Assess a completed execution round from supplied review, integration, change promotion, and verification records. Check for missing or conflicting evidence and return a script-readable result with audit details, without running tools or modifying code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing evidence after integration and change promotion
• Checking review records against integrated changes
• Detecting missing verification or cleanup evidence

Find reference solutions for CTF security challenges using challenge names, distinctive code, or error messages. Search for related writeups, extract promising pages, and compare their techniques to decide which approach may fit the current challenge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding reference solutions when a CTF challenge stalls
• Searching with distinctive code or error messages
• Comparing techniques used in similar challenges

Start unfamiliar CTF challenges by examining files, descriptions, and remote services, then route the work to an appropriate specialist skill. Guides category changes when progress stalls, checks candidate answers, and hands off to a solution write-up skill.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding a starting point for unfamiliar CTF challenges
• Choosing a specialist skill from files and service behavior
• Reassessing categories when an approach stalls

Investigate AI and machine learning CTF challenges by inspecting model weights, comparing training changes, and exploring adversarial inputs that cause misclassification. Includes references for prompt injection, model reconstruction, and identifying possible training data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Inspecting model weights and LoRA adapters
• Creating inputs that cause misclassification
• Exploring prompt injection in LLM challenges

Analyze CTF evidence such as disk images, memory dumps, logs, and network captures to recover files and trace activity. Includes techniques for finding hidden data in images, audio, and PDFs, plus hardware signal analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recovering deleted files from disk images
• Tracing activity in memory dumps and Windows logs
• Reconstructing communications and transferred data from PCAP files

Investigate CTF clues through OSINT, research using publicly available information. Use image searches, social profiles, DNS records, and archived pages to identify locations, trace accounts, and connect evidence from multiple public sources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Identifying a photo location from signs and landmarks
• Tracing usernames and account history across platforms
• Investigating DNS records and archived web pages

Develop exploits for CTF binaries with known memory handling weaknesses. Inspect protections, debug failures, and choose techniques for stack, heap, or kernel bugs to turn an identified flaw into code execution or elevated privileges.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing an exploit strategy from binary protections
• Debugging stack overflows and constructing ROP chains
• Investigating heap corruption and use-after-free bugs

Understand how CTF challenge programs work through reverse engineering, the analysis of compiled software. Use guidance on binaries, APKs, WASM, firmware, and custom virtual machines to trace validation logic, investigate obfuscation, and choose analysis tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing input validation in CTF binaries
• Investigating APK and WASM challenge behavior
• Understanding obfuscation and anti-debugging checks

Explore CTF puzzles that span categories or use unusual formats, including layered encodings, restricted Python or Bash environments, QR codes, audio signals, and logic games. Provides technique references for decoding clues and solving constraints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Decoding layered text encodings and QR puzzles
• Analyzing restricted Python or Bash environments
• Extracting clues from Morse audio and radio signals

Work through CTF challenges involving web applications, APIs, and browser behavior. Map requests and hidden features, investigate injection or authentication flaws, and build small proofs before combining weaknesses into a path to the challenge flag.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping web requests and hidden application features
• Investigating injection flaws in CTF applications
• Checking authentication, sessions, and access controls

Analyze malware in CTF security challenges using techniques for obfuscated scripts, executable files, encrypted traffic, and memory dumps. Follow references to extract configurations, identify command-and-control servers, and find indicators of compromise, such as suspicious domains.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deobfuscating JavaScript and PowerShell in CTF challenges
• Extracting malware configurations and server addresses
• Investigating encrypted traffic in packet captures

Analyze cryptography challenges in CTF security competitions by matching clues to known weaknesses in encryption, signatures, and random number generators. Use technique summaries and supporting code examples to work toward recovering plaintext or keys.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find an approach to an RSA challenge
• Investigate weaknesses in AES encryption
• Recover or predict a random generator's state

Use an unfinished teaching template to practice test-first development, building one behavior at a time. It defines how to verify a failing test, while leaving implementation and refactoring steps for the learner to complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning to start with a failing test
• Completing a test-first development exercise
• Checking why a new test fails