security & testing Claude 스킬을 발견하세요. 105개의 스킬을 탐색하고 AI 워크플로우에 완벽한 기능을 찾아보세요.
Secures LLM applications by implementing prompt injection detection, PII redaction, and output content filtering.
Automates the remediation of incomplete software projects by iteratively satisfying 19 distinct quality gates across backend, frontend, and infrastructure.
Enforces a strict Red-Green-Refactor workflow to ensure all code is verified by failing tests before implementation.
Automatically redacts sensitive personal data from logs and outputs to ensure regulatory compliance and data privacy.
Manages secure credential access and secret injection using the 1Password CLI within Claude Code environments.
Enforces a rigorous verification-first workflow by requiring fresh command evidence before any completion or success claims are made.
Systematically traces software bugs backward through the execution stack to identify and resolve original triggers.
Enables developers to create custom guardrails and automation rules for Claude Code by defining patterns that trigger specific warnings or actions.
Provides expert guidance and automated command patterns for escalating privileges on Windows systems during security audits.
Identifies and exploits Linux privilege escalation vectors including SUID binaries, sudo misconfigurations, and kernel vulnerabilities.
Performs comprehensive security audits and vulnerability assessments to identify OWASP risks and hardcoded secrets.
Facilitates advanced file transfers and data exfiltration across Linux and Windows using diverse protocols and living-off-the-land techniques.
Prevents credential leaks by automatically scanning and removing hardcoded secrets before packaging codebases with Repomix.
Diagnoses root causes and implements precise fixes for code errors, crashes, and unexpected behaviors.
Identifies security vulnerabilities and provides practical, framework-specific remediation strategies to ensure code safety.
Classifies code issues, security findings, and review comments into prioritized severity levels to streamline triage and merge decisions.
Audits cloud-native architectures and codebases to ensure high reliability, security, and operational readiness.
Automates the creation of robust unit and integration tests using industry-standard patterns and framework detection.
Automates the management of PM2 processes for serving Playwright test reports and trace viewers in development environments.
Manages the end-to-end lifecycle of security vulnerability reports and patches through coordinated disclosure and timely communication.
Conducts professional Active Directory penetration testing and security assessments using industry-standard tools and methodologies.
Conducts authorized social engineering assessments, phishing simulations, and credential harvesting to test organizational security awareness.
Automates and guides wireless network security assessments, including WPA/WPA2 cracking, WPS exploitation, and Evil Twin attacks.
Identifies and exploits security misconfigurations across AWS, Azure, and GCP environments to harden cloud infrastructure.
Automates browser-based end-to-end testing to ensure reliable user journeys across web applications using Playwright, Cypress, and Selenium.
Performs deep, context-aware Python code reviews on changed files to identify security vulnerabilities, performance bottlenecks, and architectural issues.
Orchestrates step-by-step connections for cloud logs, SaaS applications, and third-party telemetry into the LimaCharlie SecOps platform.
Manages, deploys, and troubleshoots LimaCharlie endpoint sensors across Windows, macOS, and Linux platforms for real-time EDR telemetry.
Verifies code type safety and function signature compatibility using Language Server Protocol data to prevent runtime errors.
Configures and troubleshoots LimaCharlie adapters to seamlessly ingest telemetry from cloud services, identity providers, and various log sources.
Scroll for more results...