테스트·보안 스킬

Design metrics that measure whether a workflow achieved its intended outcome using recorded session evidence. Choose built-in checks or custom JavaScript, retain suitable Bash evaluators, and define tests that distinguish success, failure, and missing evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define outcome metrics for a workflow
• Build evaluators from recorded session evidence
• Migrate existing Bash evaluators

Review git and gh operations in gh-aw workflows to check credential availability for each repository. Identify missing token handoffs, risky expansions of limited checkouts, and error handling needed where credentials are intentionally unavailable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing git operations after repository checkout
• Checking tokens for private cross-repository access
• Reviewing sparse and shallow checkout changes

Explore web application vulnerabilities by class, including access control failures, XSS, and SQL injection. Use root causes, testing checklists, and examples to plan investigations and distinguish observable security impact from an initial warning sign.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Study root causes of common web vulnerabilities
• Plan checks for cross-user access control failures
• Investigate upload and authentication weaknesses

Evaluate security findings before writing a bug bounty report. Check reproducibility, scope, practical impact, duplicates, and behavior across user sessions, then use submission checklists and CVSS 3.1 guidance to prepare evidence and assess severity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deciding whether a finding is ready to report
• Rechecking access across different user sessions
• Reviewing duplicate or intended behavior

Find test inputs and bypass references for web security checks, including XSS, SQL injection, and access control flaws. Use the guidance to investigate impact and assess whether a finding is suitable for a vulnerability report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding test inputs for web vulnerability checks
• Reviewing WAF bypass techniques and response differences
• Tracing user input into risky browser operations

Plan bug bounty sessions around a clear goal and selected vulnerability types. Guides movement through reconnaissance, mapping, discovery, proof, and reporting, with prompts and routing to help decide what to investigate next.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set the goal for a hunting session
• Decide what to investigate next
• Map application roles and trust boundaries

Audit MCP servers, which connect AI agents to external tools, for injected instructions, excessive access, secret leaks, and unapproved actions. Trace untrusted input through tool calls and document demonstrated issues with concrete fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing a custom MCP server
• Reviewing third-party tool integrations
• Checking client connection settings

Test Android and iOS apps by capturing real app traffic and checking backend APIs. When traffic is blocked or cannot be replayed, use decompilation and runtime inspection to uncover endpoints, inspect secrets, or understand request signing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Capturing mobile app traffic and testing backend APIs
• Finding hidden API endpoints and embedded credentials
• Investigating certificate pinning that blocks traffic inspection

Test web APIs, authentication, and LLM features with six Python scanners. Check cross-site access rules, header injection, database inputs, and signed login tokens, then investigate hidden server behavior through external callbacks and chatbot responses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking CORS and response-header behavior
• Testing NoSQL logins and JWT authentication
• Confirming hidden bugs through external callbacks

Turn validated security findings into clear bug bounty reports for HackerOne, Bugcrowd, Intigriti, or Immunefi. Provides templates, reproducible evidence structure, severity scoring guidance, and submission checks focused on demonstrated impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Draft a report for a specific bounty platform
• Document reproducible requests and evidence
• Explain severity using demonstrated impact

Map a website’s exposed services by collecting subdomains, active hosts, and current or historical URLs. Inspect JavaScript and exposed files, prioritize areas for security testing, and monitor new subdomains and GitHub commits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Mapping subdomains and active hosts
• Prioritizing API and authentication endpoints
• Inspecting JavaScript and exposed files

Guide bug bounty work from target research and vulnerability hunting through validation and reporting. Compare authenticated users, investigate related weaknesses, and organize reproducible evidence of practical impact before preparing a submission.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning research for an authorized bug bounty target
• Comparing API access between two test accounts
• Reviewing source code for security weaknesses

Review CI/CD pipelines, the workflows that build and release software, for unsafe code execution, exposed secrets, and excessive permissions. Combine automated scanning with manual checks to document reproducible findings and suggested fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing GitHub Actions workflows
• Checking secrets and token permissions
• Inspecting self-hosted runners

Assess what exposed credentials can access in AWS, GCP, and Azure. Map permissions, test paths to higher privileges, and document demonstrated impact using benign test objects within an explicitly authorized assessment scope.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assessing the impact of exposed cloud credentials
• Reviewing paths to higher cloud privileges
• Checking storage access with benign test objects

Guide a bug bounty investigation from scope checks and asset discovery to vulnerability testing, impact validation, and report writing. Covers web applications, source code, and AI features, with an emphasis on reproducible evidence of real harm.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning an investigation for a new bug bounty target
• Reviewing source code for risky implementation patterns
• Testing web and AI features for security flaws

Review DeFi smart contracts using ten vulnerability classes, related-function comparisons, and code search patterns. Includes target selection criteria and a Foundry test template for building reproducible proofs of security issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a DeFi target worth auditing
• Compare related functions for missing checks
• Review accounting and price handling

Investigate API requests that fail to replay because of client-generated signatures or anti-bot tokens. Start with captured traffic, identify the blocking inputs or signing function, and validate a reproducible request for further security testing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate signature errors in replayed API requests
• Trace signing functions and their inputs
• Validate a reproduced signer against browser output

Plan explicitly permitted credential testing, from preparing password candidates and usernames to choosing a login mode. Covers breach-frequency ranking, attempt pacing, success detection, audit logs, and conditions for stopping the test.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess whether credential testing is permitted and practical
• Prepare target-specific candidates and usernames
• Choose a mode for the login system

Audit GraphQL APIs for exposed schemas, missing access checks, injection risks, and weak query limits. Combine automated tools with targeted checks to investigate data exposure, unauthorized operations, and resource exhaustion, then document findings with reproducible evidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discover GraphQL schemas and hidden fields
• Check object and field access permissions
• Test batching, query depth, and complexity limits

Review EVM and Solana tokens for hidden minting, blocked sales, fee changes, and liquidity withdrawal risks. Combine code scanning with checks of privileged controls to identify mechanisms that could enable a rug pull, or issuer exit scam.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing token risks before an investment
• Checking Solana mint and freeze authorities
• Scanning token code for suspicious controls

Test LLM applications for malicious instructions, information leaks, and unsafe tool use. The skill runs attack cases and checks observable evidence, helping distinguish suspicious replies from reproducible failures with concrete impact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Test chat APIs for prompt injection
• Check document-based AI for hidden instructions
• Verify unsafe tool calls by an AI agent

Audit a deployed AI agent through its product interface to test tool misuse, cross-user memory leaks, and unauthorized actions. Focuses on observable actions and reproducible evidence, including whether required human confirmation can be bypassed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing whether an agent misuses connected tools
• Checking persistent memory for cross-user data leaks
• Testing access to another agent's conversation context

Advance one queued QA task by adding tests or test tooling, recording the work, and opening a pull request. The skill also manages its in-flight QA requests and merges into auto-qa after CI passes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing a queued unit or regression test
• Setting up test infrastructure and CI checks
• Checking and advancing an in-flight QA pull request

Find a valuable gap in test coverage by checking code, existing tests, and QA priorities. The skill creates at most one locked GitHub issue with concrete test cases, ready for later implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding past bugs that lack regression tests
• Reviewing recent changes for untested behavior
• Preparing a QA backlog without implementing tests