prompt-hacking
Advanced prompt manipulation including direct attacks, indirect injection, and multi-turn exploitation
发现 工具与集成 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Advanced prompt manipulation including direct attacks, indirect injection, and multi-turn exploitation
Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods
Defensive techniques using adversarial examples to improve model robustness and security
CI/CD integration and automation frameworks for continuous AI security testing
Test AI systems for code injection vulnerabilities including prompt-to-code attacks and agent exploitation
Techniques to extract model weights, architecture, and training data through API queries
Professional certifications, CTF competitions, and training resources for AI security practitioners
Professional security report generation, executive summaries, finding documentation, and remediation tracking
Comprehensive security testing automation for AI/ML systems with CI/CD integration
Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
Git fundamentals - init, add, commit, status, log, and core concepts
Daily Git workflow - add, commit, push, pull cycle for everyday development
Team collaboration - remote, fetch, pull, push, clone, and team workflows
Git branching strategies - create, switch, merge, rebase, and workflows
GitHub platform features - PRs, issues, actions, projects, and automation
Introduction to Git version control - what, why, and first steps
Advanced Git - interactive rebase, cherry-pick, bisect, reflog, and power user operations
Use when about to claim work is complete, fixed, or passing. Run verification commands and confirm output before making any success claims. Evidence before assertions.
Use when implementing any feature or bugfix. Write the test first, watch it fail, write minimal code to pass. Red-Green-Refactor cycle.
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when executing implementation plans with independent tasks. Dispatches subagents per task with two-stage review (spec then quality).
Use when you have a written implementation plan to execute. Load plan, review critically, execute tasks in batches with verification.
Use when you have a spec or requirements for a multi-step task, before touching code. Creates detailed implementation plans with bite-sized tasks.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。