Use when assessing an AI/ML system or LLM agent for prompt injection, jailbreaks, model inversion, data poisoning or tool abuse.
Terminal is for Claude Code, Codex, Cursor and Copilot.
Packed by SkillHub from alirezarezvani/claude-skills, always the latest version. On a phone: download now, upload later from a computer.
Use when assessing an AI/ML system or LLM agent for prompt injection, jailbreaks, model inversion, data poisoning or tool abuse.
Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent.
Expert guidance for ffuf-based web penetration testing and result analysis.
Best practices for authentication with Better Auth library.