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。
Implements a rigorous four-phase methodology to identify root causes and resolve technical issues without trial-and-error thrashing.
Performs comprehensive web application security audits by intercepting HTTP traffic, modifying requests, and identifying vulnerabilities using Burp Suite.
Conducts comprehensive security assessments and fuzzing on REST, GraphQL, and SOAP APIs to identify vulnerabilities like IDOR, injection, and authentication bypasses.
Configures and tests essential network services like HTTP, HTTPS, SNMP, and SMB for security research and penetration testing lab environments.
Provides comprehensive command patterns and methodologies for industry-standard network discovery and vulnerability assessment tools.
Executes systematic assessments to identify and exploit security misconfigurations for elevating Linux user privileges to root-level control.
Guides users through the complete penetration testing lifecycle using industry-standard tools and ethical frameworks.
Provides a comprehensive catalog of 100 critical web application vulnerabilities with detailed root causes, impacts, and remediation strategies.
Executes comprehensive web application security testing and vulnerability scanning using the industry-standard Burp Suite toolset.
Automates the end-to-end setup of evaluation pipelines for AI agents using Langfuse observability and datasets.
Enforces a strict evidence-first protocol that requires running verification commands before claiming any task is complete or passing.
Evaluates user goals across UX, code, and infrastructure layers to identify and resolve root causes of system failures.
Automates the identification and exploitation of Cross-Site Scripting (XSS) and HTML injection vulnerabilities in web applications.
Evaluates and benchmarks LLM agents using behavioral testing, reliability metrics, and adversarial strategies to ensure production readiness.
Evaluates Model Context Protocol (MCP) applications for product fit, value delivery, and user experience using automated persona-based walkthroughs.
Implements secure authentication patterns including OAuth 2.1 and API keys for Model Context Protocol (MCP) servers.
Identifies logic errors, runtime exceptions, and unhandled edge cases to ensure production-grade code reliability.
Conducts systematic production-readiness audits of backend systems across security, reliability, and performance layers.
Evaluates software readiness for alpha release by tracing end-to-end user flows from the UI to the backend to identify functional gaps.
Performs adversarial QA audits on bead-based task decompositions to ensure reliable autonomous agent execution.
Evaluates user experience, assesses production readiness, and identifies UI-to-backend gaps through structured auditing workflows.
Performs comprehensive security assessments and penetration testing on Amazon Web Services infrastructure to identify vulnerabilities and privilege escalation paths.
Ensures consistency between Langfuse prompt output contracts and function schema definitions to prevent runtime failures.
Conducts multi-perspective technical design reviews with parallel automated agents to gate implementation quality.
Implements secure operation authorization, authentication interceptors, and signed identifier tracking within the JUDO Runtime Core framework.
Implements a rigorous four-phase protocol to identify root causes and eliminate guess-and-check bug fixing.
Automates local web application testing and interaction using native Python Playwright scripts and managed server lifecycles.
Provides comprehensive guidance and command syntax for identifying and exploiting privilege escalation vulnerabilities during authorized security assessments.
Performs advanced infrastructure reconnaissance and vulnerability discovery using the Shodan search engine.
Automates end-to-end testing of web applications using AI-powered test generation and execution via the Bugster CLI.
Scroll for more results...