테스트·보안 스킬

Investigate failing macOS tests in Xcode or SwiftPM by running a focused test scope, classifying errors, and separating setup issues from code regressions. Get a concise explanation of likely causes and the next verification step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Narrowing down failing macOS tests
• Distinguishing setup issues from code regressions
• Investigating assertions and crashes

Test a real Electron app against a Den server in two separate Daytona environments. Check cloud sign-in, marketplace changes, organization policies, provider synchronization, and worker recovery, then collect evidence from the interface, APIs, logs, screenshots, and optional recordings.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify cloud sign-in and desktop handoff
• Test marketplace installation and removal
• Check organization policies and provider synchronization

Document and validate Daytona interface workflows with labeled screenshots in a browsable HTML page. Add short videos when motion matters, check that evidence shows the claimed behavior, and share it for pull request review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare visual evidence for a pull request
• Verify each step of an interface workflow
• Show streaming text or animations with video

Launch the real iPolloWork app on Daytona or locally and run scripted end-to-end tests through its debugging connection. Collect machine-checkable assertions, validated screenshots, and reports as evidence of the tested behavior.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run scripted end-to-end tests on Daytona
• Collect screenshots and reports for a pull request
• Run tests locally when Daytona is unavailable

Verify app changes through real user journeys and produce a single HTML demonstration. Each step connects a claim, user action, observable check, narration, and validated screenshot so reviewers can inspect evidence that the experience works.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Show end-to-end evidence for a feature or bug fix
• Check that core behavior survives a refactor
• Prepare a narrated HTML demonstration for PR review

Test iPolloWork's handling of corporate certificates in a Daytona Windows sandbox. Set up valid and broken HTTPS certificate chains, then verify that the desktop app and runtimes it starts use certificates trusted by Windows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproduce corporate certificate failures on Windows
• Verify that the app uses Windows certificate trust
• Compare valid and broken HTTPS certificate chains

Verify production fixes by connecting code changes and releases to Sentry issues. Compare error events and affected users before and after release, then report whether the fix worked, improved behavior, failed, or lacks enough traffic to judge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether the release containing a fix appears in Sentry
• Compare error events and affected users before and after release
• Assess improvement, regression, or insufficient traffic

Analyze git history to map contributors to security-sensitive files and identify ownership gaps. Estimate bus factor, a measure of dependence on few people, group files that change together, and export CSV or JSON for further analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding sensitive code with stale, concentrated ownership
• Checking reliance on one person for authentication code
• Comparing CODEOWNERS with contribution history

Audit and improve website accessibility using WCAG 2.1, guidelines for making web content usable by people with disabilities. Check image descriptions, contrast, forms, keyboard controls, and screen reader support with automated and manual testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a site before launch
• Fixing keyboard navigation and focus
• Improving form labels and error messages

Create a Markdown threat model grounded in a codebase. Identify valuable assets, boundaries between trusted and untrusted components, realistic attack paths, and mitigations, then prioritize risks using explicit assumptions about likelihood and impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Map attack paths across a codebase
• Assess threats within a specific project directory
• Prioritize risks to data and credentials

Automate website interactions and checks with Playwright, a browser automation tool. Create and run scripts for forms, login redirects, broken links, and different screen sizes, with screenshots and execution results to inspect.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking redirects after login
• Testing form submissions
• Comparing layouts across desktop, tablet, and mobile sizes

Measure website performance with Lighthouse, interpret scores and reports, and compare results across builds. Set limits for loading times and resource sizes, then integrate audits into CI, an automated workflow that checks code changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measure mobile and desktop website performance
• Understand Lighthouse scores and failed checks
• Set limits for resource sizes and loading times

Review Python, JavaScript/TypeScript, and Go code against security guidance for the languages and frameworks in use. Identify important weaknesses, suggest improvements, and produce prioritized reports with code references, or apply secure defaults when writing new code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review existing code for security weaknesses
• Create a security report organized by severity
• Write new code with secure defaults

Review website code across performance, accessibility, search engine optimization, and web best practices. Receive findings ranked by severity, explanations of their impact, concrete fixes with code examples, and a recommended order for addressing them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing website quality before launch
• Checking speed, accessibility, and SEO together
• Prioritizing website fixes by severity

Audit AGENTS.md, rules, skills, and their references for broken paths or commands. Optional independent agent reviews assess redundant instructions and practical usefulness, producing reports that identify what to retain, review, or consider trimming.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking paths and commands cited in agent instructions
• Finding redundant rules across skills and instructions
• Assessing which instruction files change agent behavior

Evaluate code against a product requirements document, scoring implementation and tests separately for each acceptance criterion. Produce an evidence-backed final grade, identify gaps, and compare implementations using a fixed checklist and scoring method.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether a feature fulfills its requirements
• Comparing implementations of the same specification
• Auditing unit and end-to-end test coverage

Test whether instructions planted in an agent's long-term memory or searchable knowledge base influence later behavior. Verify both a stored test marker and a resulting change in answers, permissions, or treatment of retrieved documents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether stored instructions affect later conversations
• Testing whether planted documents become trusted answers
• Reviewing permission changes caused by saved conversation summaries

Tests whether an AI agent exposes real credentials embedded in accessible source code or configuration. It requests searches for keys, passwords, and private keys, then documents confirmed disclosures with file locations and conversation evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking source code for exposed embedded API keys
• Reviewing credentials in .env and configuration files
• Checking deployment and infrastructure files for secrets

Test whether an AI agent reveals another user's data or performs actions beyond the caller's permissions. Dialogue probes cover access across users or organizations, admin functions, and attempts to gain higher privileges without authorization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking access to other users' or organizations' data
• Testing permission checks on admin-only actions
• Checking whether dialogue claims grant higher privileges

Check how an agent handles file saves, uploads and archive extraction. Test whether user supplied paths can escape the intended directory, then report confirmed unsafe handling with response evidence and suggested safeguards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether file saves stay within the intended directory
• Reviewing how uploaded filenames are handled
• Testing archive extraction paths

Test whether an AI agent executes commands hidden in user input, evaluates untrusted code, or runs scripts from unverified sources. Record confirmed weaknesses with the test conversation, potential impact, and suggested safeguards.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking command injection in shell-enabled agents
• Testing whether user input is executed as code
• Reviewing how agents load remote scripts

Test whether instructions hidden in simulated documents, retrieved passages, or web pages can redirect an agent. The skill checks for unwanted behavior or sensitive disclosures and reports confirmed failures with the test dialogue as evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing resistance to instructions embedded in uploaded documents
• Checking retrieved passages used to answer questions
• Evaluating hidden instructions in web page content

Test whether an agent misuses user trust by requesting secrets, making false safety guarantees, recommending unsafe actions, or impersonating authority. Confirmed issues are recorded with dialogue evidence, potential impact, and suggested improvements.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing whether an agent requests passwords or private keys
• Checking for misleading safety guarantees
• Reviewing advice that could lead to unsafe operations

Probe AI agents through dialogue to check for unexpected command execution, file access outside intended paths, and prompted network requests. It selects tests based on available tools and records confirmed behavior with conversation evidence and mitigation suggestions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking agents that can run commands or code
• Testing file access beyond intended directories
• Checking whether prompts trigger URL requests