테스트·보안 스킬

Organize AI agent security findings using the ten OWASP ASI risk categories. Map issues such as leaked credentials or unauthorized tool calls to category IDs, and assign severity levels with suggested remediation timeframes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify AI agent security findings
• Assign categories to leaks and unauthorized tool calls
• Organize findings from multiple detection skills

Tests communication between collaborating AI agents for private data exposure, impersonation, unsafe message channels, and unauthorized access to privileged tools. It records confirmed problems with conversation evidence, potential impact, and suggested security measures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking for private data leaks between agents
• Testing agent impersonation and message boundary bypasses
• Reviewing message encryption and shared log exposure

Test whether a browsing AI agent follows fake security verification instructions that expose stored personal information through URL paths. Examine chained navigation, memory disclosure, and constructed URLs, then document confirmed findings with evidence and mitigation suggestions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test a browsing agent's handling of malicious page instructions
• Check whether stored personal data appears in URL paths
• Inspect compliance with fake security verification pages

Assess AI products, agents, MCP servers, and skill packages through authorized security testing. It models access boundaries, tests injection and tool misuse, and produces evidence-based reports with business impact, defensive successes, and concrete remediation steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assessing an AI agent before release
• Testing prompt injection and tool misuse
• Auditing skill packages, plugins, and MCP servers

Test whether an AI agent stores hostile instructions in persistent memory and follows them later. The skill uses marked test instructions and follow-up dialogue to document storage confirmations or changes in subsequent responses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking instruction handling in long-term memory
• Testing agents with profiles or persistent notes
• Verifying whether stored instructions affect later replies

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

Check an OpenClaw environment for risky settings, unsafe skills, known software vulnerabilities, and privacy exposure. It combines local checks with optional online threat lookups and also supports reviewing individual skills before installation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Running an OpenClaw security health check
• Reviewing a skill before installation
• Auditing risks across installed skills

Test whether an AI agent reveals sensitive information through progressively stronger dialogue prompts. Check API keys, personal data, system instructions, and internal settings, then report findings only when sensitive content is actually accessible.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check for API key and credential leaks
• Test exposure of system instructions
• Inspect personal data and internal settings

Tests whether user messages can override an AI agent’s instructions or impersonate a higher authority. It checks for exposed internal instructions and changed behavior, then reports confirmed findings with prompts and responses as evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing resistance to direct instruction overrides
• Checking for exposed system or developer instructions
• Checking behavior changes caused by role impersonation

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 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

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

Write and run integration tests for GenLayer contracts in a running environment. Check agreement between the leader and validators, real web and LLM calls, and transaction execution results before deploying your contracts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check agreement between the leader and validators
• Test real web requests and LLM calls
• Run smoke tests before deployment

Writes and runs in-memory tests for GenLayer intelligent contracts. It checks state changes, permissions, and error handling, and uses simulated web and language model responses to test parsing without a server or Docker.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking contract state changes
• Testing permissions and invalid inputs
• Testing parsing with simulated web and LLM responses

Check GenLayer intelligent contracts before testing. This skill uses the GenVM linter to find forbidden code patterns, SDK usage errors, and type mismatches, with JSON output for repeated fixes and commands to extract contract interface definitions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a contract before running tests
• Finding forbidden imports and invalid storage types
• Fixing errors repeatedly using JSON results

Document visual work with real screenshots captured before a change, during key interactions, and after completion. Inspect each image and share captioned files throughout the task so users can review progress and redirect the work early.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing UI changes during implementation
• Comparing a visual bug before and after a fix
• Checking game and 3D scenes through screenshots

Evaluate work on a ten-point scale using clear criteria, then improve each item toward a chosen target. Record evidence, compare before-and-after scores, and explain any remaining gaps without rounding scores up to claim success.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improve every item to at least eight out of ten
• Compare scores and evidence before and after revisions
• Identify why an item remains below its target

Test browser games through repeatable game states and short real playthroughs. Check controls, progression, saves, device layouts, and visible feedback, then report bugs with reproduction steps, severity, and browser evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Gameplay checks before release
• Regression testing after game updates
• Touch controls and mobile layout checks

Compare a website with supplied references to identify originality risks in text, images, videos, layout, motion, and code history. Produce evidence-backed findings and practical fixes while distinguishing common design patterns from distinctive copying.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review a site against its references before release
• Check text and media for distinctive overlaps
• Find copied material in repository history

Review changes or finished work, check claims against tests, logs, running software, or source files, and explain the findings in plain language. It separates verified facts from assumptions and makes incomplete checks and remaining uncertainty clear.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Verify a bug fix against actual behavior
• Explain test results to nontechnical readers
• Check the evidence behind performance claims

Interpret n8n validation results and fix configuration, connection, and expression issues. Distinguish blocking errors from warnings and known false positives, choose suitable validation settings, review automatic fixes, and test actual outputs after structural checks pass.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understand and fix workflow validation errors
• Distinguish known false positives from real warnings
• Preview and select automatic workflow fixes

Compare five Codex execution setups on Terminal-Bench 4.0 under matching conditions. The skill covers benchmark configuration, separate verification environments, image preparation, and result interpretation to help identify misleading scores caused by setup errors.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare five Codex execution setups
• Check benchmark network and verification settings
• Prepare task and verifier container images

Review the exact final set of changes for a LoopX goal, checking reuse, simplification, concrete risks, and project validations. Record and verify a quality receipt, a review record tied to those specific changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing final changes before delivery or merge
• Checking reuse and opportunities to simplify code
• Recording validation results and concrete quality risks

Review a source tree for plausible security vulnerabilities without building or running it. The skill can use a threat model to choose review areas and produces JSON and Markdown findings for a later triage step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Screening a codebase for security issues
• Reviewing code against an existing threat model
• Preparing candidate findings for a triage workflow