发现security & testing类别的 Claude 技能。浏览 105 个技能,找到适合您 AI 工作流程的完美功能。
Deploys and configures common network services for penetration testing labs and security research environments.
Provides a comprehensive reference of essential commands and workflows for professional penetration testing and security audits.
Provides a comprehensive library of penetration testing commands for network scanning, exploitation, and vulnerability assessment.
Provides a structured methodology and comprehensive checklist for planning, executing, and managing professional penetration testing engagements.
Verifies code refactors deterministically using AST-based comparison to ensure structural changes don't introduce unintended logic modifications.
Applies adversarial thinking and robust security patterns to design, review, and harden software systems against vulnerabilities.
Identifies and tests for HTML injection vulnerabilities to secure web applications against content manipulation and phishing attacks.
Identifies and validates HTML injection vulnerabilities to secure web applications against content manipulation and phishing attacks.
Streamlines the configuration and deployment of the Quolar AI-powered test automation engine within your development environment.
Transforms Linear tickets into self-healing Playwright E2E tests with automated CI integration and PR creation.
Enforces evidence-based task completion by requiring fresh command output before making any success claims.
Provides a comprehensive framework for identifying, testing, and remediating directory traversal and Local File Inclusion (LFI) vulnerabilities in web applications.
Implements a rigorous four-phase framework to identify root causes and eliminate trial-and-error debugging thrashing.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified production code through failing tests.
Guides comprehensive security testing for REST, SOAP, and GraphQL APIs to identify vulnerabilities like IDOR and injection.
Provides expert guidance and automated workflows for security auditing, fuzzing, and vulnerability discovery across REST, SOAP, and GraphQL APIs.
Conducts comprehensive SSH security audits, credential assessments, and vulnerability exploitation to identify and remediate remote access weaknesses.
Guides users through the end-to-end process of planning, executing, and remediating penetration tests with structured methodologies.
Implements rigorous benchmarking, behavioral testing, and reliability metrics for non-deterministic LLM agents.
Tests and benchmarks LLM agents through behavioral assessment, reliability metrics, and production-grade monitoring.
Evaluates and benchmarks LLM agents using behavioral testing, reliability metrics, and adversarial assessments to ensure production-grade performance.
Guides users through a comprehensive, multi-phase methodology for planning, executing, and remediating professional penetration tests.
Provides systematic methodologies and commands for discovering and exploiting privilege escalation vulnerabilities on Windows systems during security audits.
Performs comprehensive security audits to identify, exploit, and mitigate file path traversal and Local File Inclusion (LFI) vulnerabilities.
Provides systematic methodologies and commands for discovering and exploiting privilege escalation vulnerabilities on Windows systems during security assessments.
Performs comprehensive security audits and vulnerability assessments on SMTP mail servers to identify misconfigurations and exposure risks.
Facilitates end-to-end testing and interaction with local web applications using Playwright and automated server management.
Implements Test-Driven Development principles using the Red-Green-Refactor cycle to ensure robust and maintainable code.
Automates professional reconnaissance and vulnerability discovery workflows using industry-standard red teaming tools and methodologies.
Conducts comprehensive security audits to identify, exploit, and remediate Cross-Site Scripting and HTML injection vulnerabilities in web applications.
Scroll for more results...