테스트·보안 스킬

Turn vulnerability notes, proof-of-concept code, source code, or security findings into self-contained reports. The skill checks claims against evidence, explains prerequisites and demonstrated impact, and supports both individual vulnerabilities and collections of disclosure reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning vulnerability notes into a disclosure report
• Checking source code and proof-of-concept claims
• Preparing separate reports for multiple vulnerabilities

Review pull requests, commits, branch differences, or local patches for security vulnerabilities. Inspect changed and deleted text files, trace relevant supporting code, and return validated findings, review comments, and a report describing coverage gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a pull request for security vulnerabilities
• Check a commit or branch diff before merging
• Inspect local changes, including deleted files

Audit an entire repository or a selected folder, package, or path in one review pass. Produce a security report with source evidence, severity assessments, and clear coverage limits, including unresolved questions that need further investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run a standard security audit of a repository
• Review a selected folder or package
• Check findings alongside evidence and coverage gaps

Troubleshoot browser automation when clicks, typing, scrolling, or page snapshots fail on complex websites. Inspect page structure and errors, apply waits or alternative interaction methods, and verify the fix on both problematic and simple pages.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Fix scrolling that misses a feed’s scrollable container
• Investigate clicks and text entry that have no effect
• Handle stalled or outdated page snapshots

Assess the full code change for effects on callers, configuration, and related behavior. Organize focused tests, execution evidence, and unverified areas to support decisions about whether a fix or pull request is ready.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check effects on callers of shared code
• Organize test evidence before approving a pull request
• Report unverified areas before handing off a fix

Record product demos that show real user actions and responses for each covered user journey. Add timed captions, inspect the finished clips, and include them in pull requests, with manual test instructions when recording is blocked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Showing a feature's real user flow in a pull request
• Recording CLI or API behavior in a terminal
• Adding action and result captions to demo clips

Verify Omnigent behavior through real user actions in an isolated environment. Use a feature map to cover relevant web, terminal, and CLI entry points, preserving recordings and other evidence for bug reproductions and fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproducing a user-facing Omnigent bug
• Comparing behavior before and after a fix
• Checking coverage across web, terminal, and CLI entry points

Test Omnigent’s native Pi integration using the real terminal interface and a local server. Verify messages sent through the web or API, recorded replies, interruption, session resumption, authentication, and model settings to investigate integration problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking message delivery from the web or API to Pi
• Verifying replies appear in the server transcript
• Testing interruption, resumption, and tool policies

Audit recovered bug reproduction tests before writing a fix or reviewing a pull request. Check that assertions reflect intended behavior, establish a valid failure on unfixed code, and verify the same test passes after the fix.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking recovered reproduction tests before fixing a bug
• Validating test evidence for a pull request
• Rewriting weak assertions around actual behavior

Test Omnigent’s Antigravity SDK integration against a live local server. Build test agents and run real conversations to check Gemini authentication, model selection, tool connections, and failures across the full execution path.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test authentication and real Gemini responses
• Verify tool connections and sub-agent delegation
• Investigate model selection failures

Test Omnigent’s Cursor SDK integration against a live local server. Build test agents, run real conversations, and check authentication, model selection, and tool connections while investigating empty responses or bridge processes left after shutdown.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test Cursor authentication and real responses
• Verify file operations and sub-agent delegation
• Investigate invalid models and empty output

Test Omnigent’s native Antigravity integration with a live local server and the real agy CLI. Verify messages traveling between the web interface and terminal, mirrored replies, permission requests, interruption, session resumption, and process cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing message delivery from the web interface to agy
• Checking terminal output against mirrored session replies
• Verifying permission requests and interruption

Run concurrent Omnigent conversations with real hosts and runners while replacing the LLM with a zero-latency mock. Read the generated report to explain response-time distributions, throughput, and failures, helping assess Omnigent's own processing overhead.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measuring performance with concurrent hosts
• Studying latency as conversation history grows
• Comparing throughput and failures under load

Test polly's coordination of coding agents using a scripted mock language model and live command-line tools. Check startup, task dispatch, safety rules, parallel delegation, and whether real agents make appropriate orchestration decisions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproducing polly orchestration bugs
• Checking safety rules with a mock language model
• Verifying delegation and cross-review with real agents

Review code or changes for exposed secrets, injection risks, weak encryption, and missing permission checks. Produce a structured report with severity, location, recommendations, and confidence, with a separate reviewer checking findings for false positives.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a module for security issues
• Checking changes for exposed secrets
• Preparing a vulnerability report with evidence

Test Omnigent’s setup, help, and terminal interactions by driving the real CLI in an isolated environment. Capture rendered screens and compare checks before and after a change to establish whether a reported interface problem was fixed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reproducing a first-run setup problem
• Inspecting menus in a narrow terminal
• Checking help text and command visibility

Test Omnigent’s GitHub Copilot SDK integration on a live local server. Build test agents, run real conversations, and inspect authentication, model selection, tool connections, policy enforcement, and leftover processes to investigate integration failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking Copilot authentication with a real conversation
• Testing model selection and tool connections
• Verifying sub-agent dispatch and policy enforcement

Plan tests for APIs, interfaces, data pipelines, and infrastructure. Choose suitable test types, prioritize critical behavior, and produce a plan with coverage targets and example cases while balancing thoroughness, execution speed, and maintenance effort.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning tests for a new feature
• Finding gaps in existing test coverage
• Choosing test types for APIs and interfaces

Review a design or web page against WCAG 2.1 AA, an accessibility standard. Organize findings on contrast, keyboard access, forms, and screen reader behavior, with severity levels and practical recommendations for fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review accessibility before design handoff
• Check text and interface color contrast
• Review keyboard navigation and focus behavior

Review an AI tool deployment with six checks covering prompt protection, dangerous commands, malicious inputs, sensitive data transfers, Chinese compliance requirements, and audit records. The result summarizes protection status, risks, and proposed hardening actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check whether system prompts can leak through logs or outputs
• Review blocking rules for dangerous commands and malicious inputs
• Identify sensitive data sent to overseas model endpoints

Check structured medical study materials, including guideline summaries, exam preparation, and insurance policy notes, before delivery. The skill validates required headings, source links, and scope statements, then guides corrections when the format fails validation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking the format of a medical guideline chapter summary
• Validating a daily medical study unit
• Reviewing source lines and disclaimers in insurance policy notes

Audit validation coverage for a completed development phase and fill missing checks. The skill updates VALIDATION.md, reconstructs missing validation records from existing project artifacts, and generates test files to address gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking validation gaps after a phase is complete
• Reconstructing missing validation records from project artifacts
• Adding test files for uncovered checks

Check implemented features through conversational acceptance testing, confirming behavior from the user's perspective. Record each result, retain testing progress, and diagnose reported problems to prepare verified repair plans for a subsequent execution step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check completed features from a user's perspective
• Resume an unfinished acceptance testing session
• Diagnose issues and prepare repair plans

Review threat mitigations after a development phase is complete and update SECURITY.md with verification results. Use an existing security record or a threat model in the phase plan to guide the review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check security mitigations after completing a development phase
• Audit mitigations documented in SECURITY.md
• Verify completed work against a threat model in PLAN.md