테스트·보안 스킬

Audit sensitive code and dependencies for security weaknesses, then verify fixes with tests and repeat checks. Reports identify severity, file locations, and remediation steps for issues involving authentication, data protection, injection attacks, and configuration.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing authentication and access controls
• Auditing payment processing code
• Checking dependencies for known vulnerabilities

Follow execution rules when testing in Agentica’s asynchronous REPL, an interactive code environment. Await tools that return pending results, and keep computation and the return statement in one code block so both execute in the same response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking tool calls in Agentica’s asynchronous REPL
• Waiting for file-reading results before processing them
• Combining computation and result return in one code block

Verify that infrastructure code is connected to the system and actually runs. Trace execution paths, check hook registration and database configuration, and test the full workflow to identify unused code or duplicate implementations before declaring completion.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking that new infrastructure is actually invoked
• Verifying hook registration and configuration
• Confirming the intended database backend is used

Use this skill for end-to-end testing of a persistence pipeline, the sequence of steps that saves data. The supplied material states this purpose but provides only placeholder instructions, without concrete checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing the full sequence of data persistence steps
• Considering end-to-end coverage for data saving
• Reviewing a skill intended for persistence testing

Analyze existing logs and source files from a completed example run to verify that intended actions actually occurred. Review every entry, classify failures and skips, and report evidence without running examples, controlling processes, or modifying files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify behavior after a completed example run
• Check whether exit-zero examples performed their intended actions
• Separate repository failures from environment restrictions

Run final checks after reviewed SDK changes, covering dependency installation, builds, types, generated declarations, linting, tests, and formatting. The workflow requires every check to pass before the work is marked complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Final verification after SDK code changes
• Checking changes to tests or build configuration
• Rechecking the full validation sequence after fixes

Investigate runtime behavior that code review and normal tests cannot resolve. Plan controlled cases, disclose commands and effects for approval, then use temporary scripts to report observed results, comparison conditions, and supporting evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating behavior that normal tests cannot explain
• Comparing latency under controlled conditions
• Checking integration failures and retry behavior

Audit JS SDK logs, exceptions, and telemetry for exposed model or tool inputs and outputs. It traces values to logging destinations, verifies suppression settings, fixes demonstrated leaks, and adds regression tests while preserving permitted operational diagnostics.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing logs for model and tool payload exposure
• Checking that data-suppression flags work
• Fixing demonstrated leaks through error logging

Measure JS SDK test coverage and identify untested behavior using coverage reports. It supports gap assessments and scoped test improvements, prioritizing public behavior, error handling, cancellation, and lifecycle paths, then reporting verification results and remaining gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing current JS SDK test coverage
• Investigating a decline in coverage metrics
• Adding tests for uncovered public behavior

Validate vulnerability findings by checking code, reachable attack paths, observable test results, and realistic prerequisites. The workflow produces evidence-backed reports and assesses binary constraints for memory corruption issues before exploit development proceeds.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify vulnerability scanner findings
• Identify unreachable code and unrealistic prerequisites
• Assess exploitation constraints for memory corruption

Investigate GitHub security incidents by querying archived public activity with BigQuery. Recover recorded details of deleted issues and pull requests, identify the accounts involved, and reconstruct timelines to check claims about repository activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reconstructing a security incident timeline
• Recovering recorded text from deleted issues or pull requests
• Checking claims about repository activity

Review code that has not yet been checked by forming security hypotheses and testing them with analysis tools. The skill records evidence, checks whether affected code is reachable, searches for related patterns, and preserves review progress across sessions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing code that has not yet received security checks
• Testing suspected vulnerabilities with analysis tools
• Searching the codebase for patterns behind confirmed findings

Check whether specific source lines ran during tests using gcov coverage data, which records code execution. Inspect one or several lines and report execution counts, with exit codes distinguishing uncovered lines from errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking whether a specific line ran during tests
• Inspecting execution counts for several lines
• Identifying lines left unexecuted by tests

Add gcov coverage measurement to C/C++ projects and see which lines, branches, and functions tests execute. The skill covers Makefile and CMake settings, test execution, and text or HTML reports that help identify untested code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding coverage measurement to a C/C++ project
• Finding lines and branches tests do not execute
• Adding optional coverage settings to Makefile or CMake

Observe running apps and binaries with Frida, a tool for inspecting programs during execution. Capture API calls, function activity, and script events in organized run folders across local, USB-connected, or remote targets.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Confirming whether a flagged dangerous function runs
• Tracing API calls in an unfamiliar app
• Investigating mobile traffic blocked by SSL pinning

Understand how unfamiliar code works from a security perspective. The skill maps architecture, follows untrusted input through the code, and searches for similar vulnerability patterns, with file and line references to support static analysis and finding validation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping unfamiliar code before security scanning
• Tracing untrusted input to dangerous operations
• Searching for variants of a known vulnerability

Collect GitHub activity and local git history as evidence for investigations, then save, filter, and share it as JSON. The skill also supports recovering deleted content from archives and checking stored evidence against its original sources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving GitHub commits, issues, and pull requests as evidence
• Examining local commits no longer linked to branches or tags
• Recovering deleted GitHub content from archives

Coordinate specialist agents to investigate suspicious activity in public GitHub repositories. Collect evidence from multiple sources, develop and test hypotheses, verify original records, and produce a report covering timelines, actors, and impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating suspicious activity in a public repository
• Recovering evidence of deleted content and commits
• Checking a vendor report against original records

Reviews lean-ctx tool calls in Claude Code session logs, separates tool defects from input mistakes, and checks existing reports. Reproducible problems are documented as GitHub issues with exact steps, expected behavior, and environment details.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failed lean-ctx tool calls
• Reviewing why a session switched to native tools
• Checking misleading or contradictory error messages

Run existing Tutti scenarios against a live agent provider, audit the captured session records, and replay them in a fresh isolated environment. Check evidence for each tested action, diagnose mismatches, and prepare verified recordings for publication.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording existing scenarios against a live provider
• Diagnosing transport or session-state replay mismatches
• Checking replay evidence for each tested action

Audit and improve Tutti tests by identifying the behavior each test protects and the realistic faults it should detect. Choose the appropriate test scope, check for duplicate coverage, control setup, and verify that required CI jobs execute the tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing whether existing tests catch meaningful failures
• Designing regression tests for a confirmed bug
• Consolidating duplicate or weak tests

Checks the visual quality of web pages, terminal interfaces, and paginated documents. Uses phone and desktop captures, light and dark themes, and an Apple design checklist to produce screenshot evidence and item-by-item verdicts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a UI after implementation or changes
• Comparing a rendered page with its design reference
• Finding clipped Japanese text and broken wrapping

Reviews completed changes against the original goal, constraints, code quality, and security. Combines hands-on checks of the actual application or API with recorded evidence, then reports blockers and a passed, failed, or inconclusive verdict.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing completed implementation work
• Checking actual behavior before a PR handoff
• Finding missed requirements and constraints

Guide authorized clickjacking tests, which examine whether embedded pages can trick users into unintended actions. The skill defines testing boundaries, alternative investigation paths, and reproduction evidence needed to support findings or document an inconclusive result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining the scope of a clickjacking assessment
• Reviewing inconsistent page embedding protections
• Organizing HTML, screenshots, and impact evidence