테스트·보안 스킬

Examine captured network traffic for hidden malware communications in DNS, ICMP, and HTTP. Analyze domain patterns, packet sizes, and traffic frequency to identify suspicious channels used for remote control or data theft.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating suspicious DNS, ICMP, or HTTP traffic
• Hunting for hidden malware control channels in packet captures
• Assessing possible data theft through unusual network traffic

Analyze DNS query logs for signs of hidden data transfers and attacker command channels. This skill uses unusual name lengths, randomness, and traffic volumes, then correlates findings with endpoint processes and estimates possible data loss.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating suspected data theft through DNS
• Finding algorithmically generated domains used by malware
• Reviewing hosts with unusually high DNS query volumes

Research malware families through Malpedia, connecting aliases, associated threat groups, and relationships between malware that loads other malware. Collect YARA rules, patterns used to identify malware, and organize references to support investigations and detection work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resolving different vendor names for the same malware
• Mapping malware associated with a threat group
• Documenting chains in which malware loads other malware

Acquire Linux memory with LiME and examine it using Volatility 3. Extract processes, network connections, command history, loaded kernel modules, and signs of injected code to support investigations of compromised Linux systems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Acquiring memory from a compromised Linux system
• Comparing process lists to investigate hidden processes
• Reviewing command history and network connections

Investigate malware hidden in boot records, UEFI firmware, or the operating system’s core. The skill guides evidence collection, boot integrity checks, firmware and memory analysis, and reporting of persistence mechanisms and remediation steps when compromise survives an OS reinstall.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating infections that survive an OS reinstall
• Examining unexplained Secure Boot integrity violations
• Finding hidden processes and suspicious kernel drivers

Map intrusion evidence to the seven stages of the Lockheed Martin Cyber Kill Chain, a model of attack progression. Show where defenses worked or missed activity, and recommend prioritized controls that could interrupt attacks earlier.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping attack progression after an incident
• Finding detection gaps at each attack stage
• Planning layered defenses to stop attacks earlier

Extract Cobalt Strike Beacon settings from executable files and memory dumps to identify command-and-control servers, communication patterns, and identifying markers. Use the findings to compare samples, investigate incidents, and develop file and network detection rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract Beacon settings from suspicious files
• Identify command-and-control servers and traffic patterns
• Compare samples using watermark identifiers

Inspect Windows startup entries with Sysinternals Autoruns to find possible malware persistence, settings that let malware restart automatically. Review signatures, file locations, and changes from a clean baseline to identify entries that need investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating suspicious startup entries on a Windows endpoint
• Comparing startup settings against a clean baseline
• Checking for remaining malware startup entries after cleanup

Investigate suspicious Azure activity by querying administrative and sign-in logs. Create KQL queries, Azure's log search language, to examine role assignments, resource changes, unusual access, and other signals for cloud security monitoring.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate suspicious administrative activity in Azure
• Check newly added administrator roles
• Review resource and network security rule changes

Audit whether an AI agent follows its intended purpose, business rules, and permission boundaries. The skill guides setup discovery, test configuration, execution against an agent endpoint or substitute model, and interpretation of scores from selected judging models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing an agent's compliance with business rules
• Testing permission boundaries and dangerous tools
• Evaluating an agent through its HTTP endpoint

Write and run tests for features and fixes, starting with likely failures and boundary cases. Use behavior-focused checks, suitable test environments, and coverage results to assess whether changes are ready.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Writing tests for a new feature
• Adding regression tests for a bug fix
• Updating existing tests after behavior changes

Test runnable software through normal and hostile end-to-end scenarios, checking complete behavior across a workflow. Investigate failures, apply fixes, rerun checks, and produce an evidence-backed report covering results, cleanup, and remaining risks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check behavior with malformed input
• Verify cancellation and resumption
• Investigate flaky tests

Review websites for security, browser compatibility, and code quality. Identify issues in HTTPS settings, third-party libraries, HTML, and error handling, then apply concrete improvements using checklists and implementation examples.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing website security settings
• Checking third-party libraries for vulnerabilities
• Replacing deprecated browser APIs

Audit websites for accessibility barriers and improve image descriptions, color contrast, forms, keyboard navigation, and screen reader support. Provides code examples and automated and manual testing guidance for work toward WCAG 2.1 AA or AAA accessibility standards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing a website for accessibility issues
• Fixing form labels and error announcements
• Checking keyboard navigation and dialog focus

Turn feature requirements into test plans, step-by-step manual tests, regression suites for checking existing features, and reproducible bug reports. The skill also supports comparing implemented interfaces with Figma designs and documenting visual differences.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan tests for a new feature
• Write manual checkout test cases
• Organize regression checks before a release

Build safety checks for LLM prompts and responses using Meta's LlamaGuard moderation model. Classify potentially harmful content, block flagged messages, serve checks through an API, and integrate them with NeMo Guardrails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking prompts before sending them to an LLM
• Filtering responses before displaying them
• Building a moderation API

Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detecting instructions that try to bypass safety rules
• Masking personal information before processing
• Adding factual checks to generated answers

Design tests that assess an AI agent's capabilities and reliability. Covers repeated runs to measure variation, checks for required behavior, and adversarial testing to expose failures that ordinary successful examples may miss.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measuring variation across repeated runs of the same test
• Checking whether an agent follows required behavior
• Testing responses to unexpected or adversarial inputs

Review security across web apps, APIs, mobile apps, Kubernetes, and AI agents using six OWASP references. Identify risky authentication, access controls, configurations, and prompt handling, then use examples and checklists to plan fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review login flows and access controls
• Check API authorization and data exposure
• Review mobile app storage and communications

Compare Storybook screenshots before and after a code change in both dark and light themes. Check rendering noise, annotate meaningful differences, and export a shareable visual report that helps reviewers see what changed and what stayed identical.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare screens before and after a code change
• Check visual regressions in dark and light themes
• Share annotated screenshot comparisons in a PR

Build Storybook page stories for SigNoz by mapping API requests, display states, and URL parameters. Use msw mock responses, which simulate API replies, and controls to inspect loading, errors, permissions, and other page states.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating Storybook stories for SigNoz pages
• Switching between loading, empty, and error states
• Checking how permissions affect buttons and controls

Process AI model responses through a specified Google Model Armor template before sending them to users. Supply response text directly, pipe output from another command, or provide a JSON request for outbound safety processing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check model responses before showing them to users
• Pipe model command output into safety processing
• Process response text with a specified template

Use Google Model Armor to filter user prompts and model responses for safety. The skill covers creating templates that define checks and discovering command parameters before making API calls through the gws command-line tool.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check user prompts through a Model Armor template
• Check model responses through a Model Armor template
• Create a template for content safety checks

Check a user prompt through an existing Google Model Armor template. Supply the text directly, submit a JSON request, or pass text through standard input, which lets the command read piped content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking an AI prompt against an existing template
• Passing prompt text from another command
• Submitting a prompt check as a JSON request